Search

Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even when the relevant visual information has been removed. This includes Personal Identifiable Information (PII) repeated once in the training set, indicating these models could divulge memorised sensitive information and therefore pose a privacy risk. We quantitatively measure the extractability of information in controlled experiments and differentiate between cases where it arises from generalization capabilities or from memorization. We further investigate the factors that influence memorization across multiple state-of-the-art models and propose an effective heuristic countermeasure that empirically prevents the extractability of PII., Comment: ICML 2024

Building generalized models that can solve many computer vision tasks simultaneously is an intriguing direction. Recent works have shown image itself can be used as a natural interface for general-purpose visual perception and demonstrated inspiring results. In this paper, we explore diffusion-based vision generalists, where we unify different types of dense prediction tasks as conditional image generation and re-purpose pre-trained diffusion models for it. However, directly applying off-the-shelf latent diffusion models leads to a quantization issue. Thus, we propose to perform diffusion in pixel space and provide a recipe for finetuning pre-trained text-to-image diffusion models for dense vision tasks. In experiments, we evaluate our method on four different types of tasks and show competitive performance to the other vision generalists., Comment: Published at CVPR 2024 as a workshop paper

Gaussian splatting has become a popular representation for novel-view synthesis, exhibiting clear strengths in efficiency, photometric quality, and compositional edibility. Following its success, many works have extended Gaussians to 4D, showing that dynamic Gaussians maintain these benefits while also tracking scene geometry far better than alternative representations. Yet, these methods assume dense multi-view videos as supervision, constraining their use to controlled capture settings. In this work, we extend the capability of Gaussian scene representations to casually captured monocular videos. We show that existing 4D Gaussian methods dramatically fail in this setup because the monocular setting is underconstrained. Building off this finding, we propose Dynamic Gaussian Marbles (DGMarbles), consisting of three core modifications that target the difficulties of the monocular setting. First, DGMarbles uses isotropic Gaussian "marbles", reducing the degrees of freedom of each Gaussian, and constraining the optimization to focus on motion and appearance over local shape. Second, DGMarbles employs a hierarchical divide-and-conquer learning strategy to guide the optimization towards solutions with coherent motion. Finally, DGMarbles adds image-level and geometry-level priors into the optimization, including a tracking loss that takes advantage of recent progress in point tracking. By constraining the optimization in these ways, DGMarbles learns Gaussian trajectories that enable novel-view rendering and accurately capture the 3D motion of the scene elements. We evaluate on the (monocular) Nvidia Dynamic Scenes dataset and the Dycheck iPhone dataset, and show that DGMarbles significantly outperforms other Gaussian baselines in quality, and is on-par with non-Gaussian representations, all while maintaining the efficiency, compositionality, editability, and tracking benefits of Gaussians.

Text-to-image models are becoming increasingly popular, revolutionizing the landscape of digital art creation by enabling highly detailed and creative visual content generation. These models have been widely employed across various domains, particularly in art generation, where they facilitate a broad spectrum of creative expression and democratize access to artistic creation. In this paper, we introduce \texttt{STYLEBREEDER}, a comprehensive dataset of 6.8M images and 1.8M prompts generated by 95K users on Artbreeder, a platform that has emerged as a significant hub for creative exploration with over 13M users. We introduce a series of tasks with this dataset aimed at identifying diverse artistic styles, generating personalized content, and recommending styles based on user interests. By documenting unique, user-generated styles that transcend conventional categories like 'cyberpunk' or 'Picasso,' we explore the potential for unique, crowd-sourced styles that could provide deep insights into the collective creative psyche of users worldwide. We also evaluate different personalization methods to enhance artistic expression and introduce a style atlas, making these models available in LoRA format for public use. Our research demonstrates the potential of text-to-image diffusion models to uncover and promote unique artistic expressions, further democratizing AI in art and fostering a more diverse and inclusive artistic community. The dataset, code and models are available at https://stylebreeder.github.io under a Public Domain (CC0) license.

Our objective is to leverage a differentiable radiance field \eg NeRF to reconstruct detailed 3D surfaces in addition to producing the standard novel view renderings. There have been related methods that perform such tasks, usually by utilizing a signed distance field (SDF). However, the state-of-the-art approaches still fail to correctly reconstruct the small-scale details, such as the leaves, ropes, and textile surfaces. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor to prioritize the rendering and zero-crossing surface fitting on top of establishing a perfect SDF. We propose to adaptively adjust the regularization on the signed distance field so that unsatisfying rendering rays won't enforce strong Eikonal regularization which is ineffective, and allow the gradients from regions with well-learned radiance to effectively back-propagated to the SDF. Consequently, balancing the two objectives in order to generate accurate and detailed surfaces. Additionally, concerning whether there is a geometric bias between the zero-crossing surface in SDF and rendering points in the radiance field, the projection becomes adjustable as well depending on different 3D locations during optimization. Our proposed \textit{RaNeuS} are extensively evaluated on both synthetic and real datasets, achieving state-of-the-art results on both novel view synthesis and geometric reconstruction., Comment: 3DV 2024, oral. In: Proceedings of the IEEE/CVF International Conference on 3D Vision (2023)

Realistic conditional 3D scene synthesis significantly enhances and accelerates the creation of virtual environments, which can also provide extensive training data for computer vision and robotics research among other applications. Diffusion models have shown great performance in related applications, e.g., making precise arrangements of unordered sets. However, these models have not been fully explored in floor-conditioned scene synthesis problems. We present MiDiffusion, a novel mixed discrete-continuous diffusion model architecture, designed to synthesize plausible 3D indoor scenes from given room types, floor plans, and potentially pre-existing objects. We represent a scene layout by a 2D floor plan and a set of objects, each defined by its category, location, size, and orientation. Our approach uniquely implements structured corruption across the mixed discrete semantic and continuous geometric domains, resulting in a better conditioned problem for the reverse denoising step. We evaluate our approach on the 3D-FRONT dataset. Our experimental results demonstrate that MiDiffusion substantially outperforms state-of-the-art autoregressive and diffusion models in floor-conditioned 3D scene synthesis. In addition, our models can handle partial object constraints via a corruption-and-masking strategy without task specific training. We show MiDiffusion maintains clear advantages over existing approaches in scene completion and furniture arrangement experiments., Comment: 19 pages, 14 figures. Under review. Code to be released at: https://github.com/MIT-SPARK/MiDiffusion

3D Gaussian Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous Localization and Mapping (SLAM), as it provides a compact dense map representation while enabling efficient and high-quality map rendering. However, existing methods show significantly worse reconstruction quality than competing methods using other 3D representations, e.g. neural points clouds, since they either do not employ global map and pose optimization or make use of monocular depth. In response, we propose the first RGB-only SLAM system with a dense 3D Gaussian map representation that utilizes all benefits of globally optimized tracking by adapting dynamically to keyframe pose and depth updates by actively deforming the 3D Gaussian map. Moreover, we find that refining the depth updates in inaccurate areas with a monocular depth estimator further improves the accuracy of the 3D reconstruction. Our experiments on the Replica, TUM-RGBD, and ScanNet datasets indicate the effectiveness of globally optimized 3D Gaussians, as the approach achieves superior or on par performance with existing RGB-only SLAM methods methods in tracking, mapping and rendering accuracy while yielding small map sizes and fast runtimes. The source code is available at https://github.com/eriksandstroem/Splat-SLAM., Comment: 21 pages

Recent advancements in Large Language Models (LLMs) have led to the development of Video Large Multi-modal Models (Video-LMMs) that can handle a wide range of video understanding tasks. These models have the potential to be deployed in real-world applications such as robotics, AI assistants, medical surgery, and autonomous vehicles. The widespread adoption of Video-LMMs in our daily lives underscores the importance of ensuring and evaluating their robust performance in mirroring human-like reasoning and interaction capabilities in complex, real-world contexts. However, existing benchmarks for Video-LMMs primarily focus on general video comprehension abilities and neglect assessing their reasoning capabilities over complex videos in the real-world context, and robustness of these models through the lens of user prompts as text queries. In this paper, we present the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES), a novel benchmark that comprehensively assesses the performance of Video-LMMs across 11 diverse real-world video dimensions. We evaluate 9 recent models, including both open-source and closed-source variants, and find that most of the Video-LMMs, especially open-source ones, struggle with robustness and reasoning when dealing with complex videos. Based on our analysis, we develop a training-free Dual-Step Contextual Prompting (DSCP) technique to enhance the performance of existing Video-LMMs. Our findings provide valuable insights for building the next generation of human-centric AI systems with advanced robustness and reasoning capabilities. Our dataset and code are publicly available at: https://mbzuai-oryx.github.io/CVRR-Evaluation-Suite/., Comment: Technical report

We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynamically adapts to scene graphs. Existing methods struggle to handle scene graphs due to varying numbers of nodes, multiple edge combinations, and manipulator-induced node-edge operations. EchoScene overcomes this by associating each node with a denoising process and enables collaborative information exchange, enhancing controllable and consistent generation aware of global constraints. This is achieved through an information echo scheme in both shape and layout branches. At every denoising step, all processes share their denoising data with an information exchange unit that combines these updates using graph convolution. The scheme ensures that the denoising processes are influenced by a holistic understanding of the scene graph, facilitating the generation of globally coherent scenes. The resulting scenes can be manipulated during inference by editing the input scene graph and sampling the noise in the diffusion model. Extensive experiments validate our approach, which maintains scene controllability and surpasses previous methods in generation fidelity. Moreover, the generated scenes are of high quality and thus directly compatible with off-the-shelf texture generation. Code and trained models are open-sourced., Comment: 25 pages. 10 figures

Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders, e.g. "blindness" to certain image features, visual hallucination, etc. To address these issues, we study broadening the visual encoding capabilities of VLMs. We first comprehensively benchmark several vision encoders with different inductive biases for solving VLM tasks. We observe that there is no single encoding configuration that consistently achieves top performance across different tasks, and encoders with different biases can perform surprisingly similarly. Motivated by this, we introduce a method, named BRAVE, that consolidates features from multiple frozen encoders into a more versatile representation that can be directly fed as the input to a frozen LM. BRAVE achieves state-of-the-art performance on a broad range of captioning and VQA benchmarks and significantly reduces the aforementioned issues of VLMs, while requiring a smaller number of trainable parameters than existing methods and having a more compressed representation. Our results highlight the potential of incorporating different visual biases for a more broad and contextualized visual understanding of VLMs., Comment: Project page at https://brave-vlms.epfl.ch/

Modeling and rendering photorealistic avatars is of crucial importance in many applications. Existing methods that build a 3D avatar from visual observations, however, struggle to reconstruct clothed humans. We introduce PhysAvatar, a novel framework that combines inverse rendering with inverse physics to automatically estimate the shape and appearance of a human from multi-view video data along with the physical parameters of the fabric of their clothes. For this purpose, we adopt a mesh-aligned 4D Gaussian technique for spatio-temporal mesh tracking as well as a physically based inverse renderer to estimate the intrinsic material properties. PhysAvatar integrates a physics simulator to estimate the physical parameters of the garments using gradient-based optimization in a principled manner. These novel capabilities enable PhysAvatar to create high-quality novel-view renderings of avatars dressed in loose-fitting clothes under motions and lighting conditions not seen in the training data. This marks a significant advancement towards modeling photorealistic digital humans using physically based inverse rendering with physics in the loop. Our project website is at: https://qingqing-zhao.github.io/PhysAvatar, Comment: Project Page: https://qingqing-zhao.github.io/PhysAvatar

Recovering the 3D scene geometry from a single view is a fundamental yet ill-posed problem in computer vision. While classical depth estimation methods infer only a 2.5D scene representation limited to the image plane, recent approaches based on radiance fields reconstruct a full 3D representation. However, these methods still struggle with occluded regions since inferring geometry without visual observation requires (i) semantic knowledge of the surroundings, and (ii) reasoning about spatial context. We propose KYN, a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density. We introduce a vision-language modulation module to enrich point features with fine-grained semantic information. We aggregate point representations across the scene through a language-guided spatial attention mechanism to yield per-point density predictions aware of the 3D semantic context. We show that KYN improves 3D shape recovery compared to predicting density for each 3D point in isolation. We achieve state-of-the-art results in scene and object reconstruction on KITTI-360, and show improved zero-shot generalization compared to prior work. Project page: https://ruili3.github.io/kyn., Comment: CVPR 2024. Project page: https://ruili3.github.io/kyn

Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the visual-language models. Indeed, point cloud and 3D meshes typically have a lower resolution than images and the reconstructed 3D scene geometry might not project well to the underlying 2D image sequences used to compute pixel-aligned CLIP features. To address these challenges, we propose OpenNeRF which naturally operates on posed images and directly encodes the VLM features within the NeRF. This is similar in spirit to LERF, however our work shows that using pixel-wise VLM features (instead of global CLIP features) results in an overall less complex architecture without the need for additional DINO regularization. Our OpenNeRF further leverages NeRF's ability to render novel views and extract open-set VLM features from areas that are not well observed in the initial posed images. For 3D point cloud segmentation on the Replica dataset, OpenNeRF outperforms recent open-vocabulary methods such as LERF and OpenScene by at least +4.9 mIoU., Comment: ICLR 2024, Project page: https://opennerf.github.io

Synthesizing realistic and diverse indoor 3D scene layouts in a controllable fashion opens up applications in simulated navigation and virtual reality. As concise and robust representations of a scene, scene graphs have proven to be well-suited as the semantic control on the generated layout. We present a variant of the conditional variational autoencoder (cVAE) model to synthesize 3D scenes from scene graphs and floor plans. We exploit the properties of self-attention layers to capture high-level relationships between objects in a scene, and use these as the building blocks of our model. Our model, leverages graph transformers to estimate the size, dimension and orientation of the objects in a room while satisfying relationships in the given scene graph. Our experiments shows self-attention layers leads to sparser (7.9x compared to Graphto3D) and more diverse scenes (16%)., Comment: Some authors were not timely informed of the submission

Existing deep learning methods for the reconstruction and denoising of point clouds rely on small datasets of 3D shapes. We circumvent the problem by leveraging deep learning methods trained on billions of images. We propose a method to reconstruct point clouds from few images and to denoise point clouds from their rendering by exploiting prior knowledge distilled from image-based deep learning models. To improve reconstruction in constraint settings, we regularize the training of a differentiable renderer with hybrid surface and appearance by introducing semantic consistency supervision. In addition, we propose a pipeline to finetune Stable Diffusion to denoise renderings of noisy point clouds and we demonstrate how these learned filters can be used to remove point cloud noise coming without 3D supervision. We compare our method with DSS and PointRadiance and achieved higher quality 3D reconstruction on the Sketchfab Testset and SCUT Dataset., Comment: An author was not timely informed before the released submission

We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multiple modalities, including object-level point clouds, images, attributes, and relationships between objects, offering a lightweight and efficient alternative to conventional methods that rely on extensive image databases. Given the available modalities, the proposed method SceneGraphLoc learns a fixed-sized embedding for each node (i.e., representing an object instance) in the scene graph, enabling effective matching with the objects visible in the input query image. This strategy significantly outperforms other cross-modal methods, even without incorporating images into the map embeddings. When images are leveraged, SceneGraphLoc achieves performance close to that of state-of-the-art techniques depending on large image databases, while requiring three orders-of-magnitude less storage and operating orders-of-magnitude faster. The code will be made public.

Low-Rank Adaptations (LoRAs) have emerged as a powerful and popular technique in the field of image generation, offering a highly effective way to adapt and refine pre-trained deep learning models for specific tasks without the need for comprehensive retraining. By employing pre-trained LoRA models, such as those representing a specific cat and a particular dog, the objective is to generate an image that faithfully embodies both animals as defined by the LoRAs. However, the task of seamlessly blending multiple concept LoRAs to capture a variety of concepts in one image proves to be a significant challenge. Common approaches often fall short, primarily because the attention mechanisms within different LoRA models overlap, leading to scenarios where one concept may be completely ignored (e.g., omitting the dog) or where concepts are incorrectly combined (e.g., producing an image of two cats instead of one cat and one dog). To overcome these issues, CLoRA addresses them by updating the attention maps of multiple LoRA models and leveraging them to create semantic masks that facilitate the fusion of latent representations. Our method enables the creation of composite images that truly reflect the characteristics of each LoRA, successfully merging multiple concepts or styles. Our comprehensive evaluations, both qualitative and quantitative, demonstrate that our approach outperforms existing methodologies, marking a significant advancement in the field of image generation with LoRAs. Furthermore, we share our source code, benchmark dataset, and trained LoRA models to promote further research on this topic.

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level by integrating them with feature extraction techniques. The outlined method exploits such a novel view synthesizer to expand a sparse set of RGB-only reference views for the zero-shot 6D pose estimation task. Experiments are quantitatively analyzed on the CO3D dataset, showcasing increased performance over baselines, a substantial reduction in data requirements, and the removal of the necessity of depth information., Comment: 6 pages, 2 reference pages, 4 figures

Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-the-art quality in challenging scenarios such as in-the-wild captures and large-scale scenes, they often suffer from excessively high compute requirements linked to volumetric rendering. Gaussian Splatting-based methods, on the other hand, rely on rasterization and naturally achieve real-time rendering but suffer from brittle optimization heuristics that underperform on more challenging scenes. In this work, we present RadSplat, a lightweight method for robust real-time rendering of complex scenes. Our main contributions are threefold. First, we use radiance fields as a prior and supervision signal for optimizing point-based scene representations, leading to improved quality and more robust optimization. Next, we develop a novel pruning technique reducing the overall point count while maintaining high quality, leading to smaller and more compact scene representations with faster inference speeds. Finally, we propose a novel test-time filtering approach that further accelerates rendering and allows to scale to larger, house-sized scenes. We find that our method enables state-of-the-art synthesis of complex captures at 900+ FPS., Comment: Project page at https://m-niemeyer.github.io/radsplat/

During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved, especially in non-textured regions such as walls, ceilings, and furniture surfaces. This degradation significantly affects the rendering quality of novel views that deviate significantly from the viewpoints in the training data. To mitigate this issue, we propose a novel approach called GeoGaussian. Based on the smoothly connected areas observed from point clouds, this method introduces a novel pipeline to initialize thin Gaussians aligned with the surfaces, where the characteristic can be transferred to new generations through a carefully designed densification strategy. Finally, the pipeline ensures that the scene's geometry and texture are maintained through constrained optimization processes with explicit geometry constraints. Benefiting from the proposed architecture, the generative ability of 3D Gaussians is enhanced, especially in structured regions. Our proposed pipeline achieves state-of-the-art performance in novel view synthesis and geometric reconstruction, as evaluated qualitatively and quantitatively on public datasets.

In this paper, we present KP-RED, a unified KeyPoint-driven REtrieval and Deformation framework that takes object scans as input and jointly retrieves and deforms the most geometrically similar CAD models from a pre-processed database to tightly match the target. Unlike existing dense matching based methods that typically struggle with noisy partial scans, we propose to leverage category-consistent sparse keypoints to naturally handle both full and partial object scans. Specifically, we first employ a lightweight retrieval module to establish a keypoint-based embedding space, measuring the similarity among objects by dynamically aggregating deformation-aware local-global features around extracted keypoints. Objects that are close in the embedding space are considered similar in geometry. Then we introduce the neural cage-based deformation module that estimates the influence vector of each keypoint upon cage vertices inside its local support region to control the deformation of the retrieved shape. Extensive experiments on the synthetic dataset PartNet and the real-world dataset Scan2CAD demonstrate that KP-RED surpasses existing state-of-the-art approaches by a large margin. Codes and trained models will be released in https://github.com/lolrudy/KP-RED., Comment: Accepted by CVPR 2024

We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks. Our novel contributions enhance CLIP on both the vision and text sides. On the vision side, we incorporate ROI heatmaps emulating human visual attention mechanisms to emphasize subject-relevant image regions. On the text side, we introduce human pose descriptions to provide rich contextual information. For human-centric tasks, FocusCLIP is trained with images from the MPII Human Pose dataset. The proposed approach surpassed CLIP by an average of 8.61% across five previously unseen datasets covering three human-centric tasks. FocusCLIP achieved an average accuracy of 33.65% compared to 25.04% by CLIP. We observed a 3.98% improvement in activity recognition, a 14.78% improvement in age classification, and a 7.06% improvement in emotion recognition. Moreover, using our proposed single-shot LLM prompting strategy, we release a high-quality MPII Pose Descriptions dataset to encourage further research in multimodal learning for human-centric tasks. Furthermore, we also demonstrate the effectiveness of our subject-level supervision on non-human-centric tasks. FocusCLIP shows a 2.47% improvement over CLIP in zero-shot bird classification using the CUB dataset. Our findings emphasize the potential of integrating subject-level guidance with general pretraining methods for enhanced downstream performance.

3D shape generation from text is a fundamental task in 3D representation learning. The text-shape pairs exhibit a hierarchical structure, where a general text like ``chair" covers all 3D shapes of the chair, while more detailed prompts refer to more specific shapes. Furthermore, both text and 3D shapes are inherently hierarchical structures. However, existing Text2Shape methods, such as SDFusion, do not exploit that. In this work, we propose HyperSDFusion, a dual-branch diffusion model that generates 3D shapes from a given text. Since hyperbolic space is suitable for handling hierarchical data, we propose to learn the hierarchical representations of text and 3D shapes in hyperbolic space. First, we introduce a hyperbolic text-image encoder to learn the sequential and multi-modal hierarchical features of text in hyperbolic space. In addition, we design a hyperbolic text-graph convolution module to learn the hierarchical features of text in hyperbolic space. In order to fully utilize these text features, we introduce a dual-branch structure to embed text features in 3D feature space. At last, to endow the generated 3D shapes with a hierarchical structure, we devise a hyperbolic hierarchical loss. Our method is the first to explore the hyperbolic hierarchical representation for text-to-shape generation. Experimental results on the existing text-to-shape paired dataset, Text2Shape, achieved state-of-the-art results. We release our implementation under HyperSDFusion.github.io.

This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html., Comment: Our OpenSUN3D workshop website for ICCV 2023: https://opensun3d.github.io/index_iccv23.html

In robotics, it's crucial to understand object deformation during tactile interactions. A precise understanding of deformation can elevate robotic simulations and have broad implications across different industries. We introduce a method using Physics-Encoded Graph Neural Networks (GNNs) for such predictions. Similar to robotic grasping and manipulation scenarios, we focus on modeling the dynamics between a rigid mesh contacting a deformable mesh under external forces. Our approach represents both the soft body and the rigid body within graph structures, where nodes hold the physical states of the meshes. We also incorporate cross-attention mechanisms to capture the interplay between the objects. By jointly learning geometry and physics, our model reconstructs consistent and detailed deformations. We've made our code and dataset public to advance research in robotic simulation and grasping., Comment: Accepted at 2024 IEEE International Conference on Robotics and Automation (ICRA2024)

Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance fields excel at view synthesis and 3D reconstruction, they cannot synthesize plausible details in unobserved regions since they lack a generative capability. Conversely, existing generative methods are typically not capable of reconstructing detailed, large-scale scenes in the wild, as they use limited-capacity 3D scene representations, require aligned camera poses, or rely on additional regularizers. In this work, we introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. To achieve this, we make three contributions. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes, dynamically allocating more capacity as needed to capture details visible in each image. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images without the need for any additional supervision signal such as masks or depths. This supports 3D reconstruction and generation in a unified architecture. Third, we develop a principled approach to avoid trivial 3D solutions when integrating the image-based rendering with the diffusion model, by dropping out representations of some images. We evaluate the model on several challenging datasets of real and synthetic images, and demonstrate superior results on generation, novel view synthesis and 3D reconstruction., Comment: Accepted at ICLR 2024. Project page: https://anciukevicius.github.io/generative-image-based-rendering

We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes. Based on a user-provided textual description and a 2D bounding box in a reference viewpoint, InseRF generates new objects in 3D scenes. Recently, methods for 3D scene editing have been profoundly transformed, owing to the use of strong priors of text-to-image diffusion models in 3D generative modeling. Existing methods are mostly effective in editing 3D scenes via style and appearance changes or removing existing objects. Generating new objects, however, remains a challenge for such methods, which we address in this study. Specifically, we propose grounding the 3D object insertion to a 2D object insertion in a reference view of the scene. The 2D edit is then lifted to 3D using a single-view object reconstruction method. The reconstructed object is then inserted into the scene, guided by the priors of monocular depth estimation methods. We evaluate our method on various 3D scenes and provide an in-depth analysis of the proposed components. Our experiments with generative insertion of objects in several 3D scenes indicate the effectiveness of our method compared to the existing methods. InseRF is capable of controllable and 3D-consistent object insertion without requiring explicit 3D information as input. Please visit our project page at https://mohamad-shahbazi.github.io/inserf.

Foundational vision-language models such as CLIP are becoming a new paradigm in vision, due to their excellent generalization abilities. However, adapting these models for downstream tasks while maintaining their generalization remains a challenge. In literature, one branch of methods adapts CLIP by learning prompts using visual information. While effective, most of these works require labeled data which is not practical, and often struggle to generalize towards new datasets due to over-fitting on the source data. An alternative approach resorts to training-free methods by generating class descriptions from large language models (LLMs) and perform prompt ensembling. However, these methods often generate class specific prompts that cannot be transferred to other classes, which incur higher costs by generating LLM descriptions for each class separately. In this work, we propose to combine the strengths of these both streams of methods by learning prompts using only text data derived from LLMs. As supervised training of prompts is not trivial due to absence of images, we develop a training approach that allows prompts to extract rich contextual knowledge from LLM data. Moreover, with LLM contextual data mapped within the learned prompts, it enables zero-shot transfer of prompts to new classes and datasets potentially cutting the LLM prompt engineering cost. To the best of our knowledge, this is the first work that learns generalized prompts using text only data. We perform extensive evaluations on 4 benchmarks where our method improves over prior ensembling works while being competitive to those utilizing labeled images. Our code and pre-trained models are available at https://github.com/muzairkhattak/ProText., Comment: Project Page: https://muzairkhattak.github.io/ProText/

Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically struggle to recognize object classes beyond the annotated classes, i.e., they do not generalize well to unseen domains and require additional domain-specific annotations. In contrast, 2D foundation models demonstrate strong generalization and impressive zero-shot abilities, inspiring us to incorporate these characteristics from 2D models into 3D models. Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation. We propose Segment3D, a method for class-agnostic 3D scene segmentation that produces high-quality 3D segmentation masks. It improves over existing 3D segmentation models (especially on fine-grained masks), and enables easily adding new training data to further boost the segmentation performance -- all without the need for manual training labels., Comment: Project Page: http://segment3d.github.io

Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images. However, reconstructing real-world captures of complex scenes still remains a challenge. Existing generic 3D reconstruction methods often struggle to represent fine geometric details and do not adequately model reflective surfaces of large-scale scenes. Techniques that explicitly focus on reflective surfaces can model complex and detailed reflections by exploiting better reflection parameterizations. However, we observe that these methods are often not robust in real unbounded scenarios where non-reflective as well as reflective components are present. In this work, we propose UniSDF, a general purpose 3D reconstruction method that can reconstruct large complex scenes with reflections. We investigate both view-based as well as reflection-based color prediction parameterization techniques and find that explicitly blending these representations in 3D space enables reconstruction of surfaces that are more geometrically accurate, especially for reflective surfaces. We further combine this representation with a multi-resolution grid backbone that is trained in a coarse-to-fine manner, enabling faster reconstructions than prior methods. Extensive experiments on object-level datasets DTU, Shiny Blender as well as unbounded datasets Mip-NeRF 360 and Ref-NeRF real demonstrate that our method is able to robustly reconstruct complex large-scale scenes with fine details and reflective surfaces. Please see our project page at https://fangjinhuawang.github.io/UniSDF., Comment: Project page: https://fangjinhuawang.github.io/UniSDF

In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can process long videos conditioned on a task, together with a training method that enables it to bridge pre-trained visual and language models; (ii) we identify tasks that could benefit from longer video perception; and (iii) we empirically validate its efficacy on a wide variety of evaluation tasks including NextQA, EgoSchema, and the EGO4D-LTA challenge.

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality, varied images, with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A significant challenge within this domain is localized editing, where specific areas of an image are modified without affecting the rest of the content. This paper introduces LIME for localized image editing in diffusion models that do not require user-specified regions of interest (RoI) or additional text input. Our method employs features from pre-trained methods and a simple clustering technique to obtain precise semantic segmentation maps. Then, by leveraging cross-attention maps, it refines these segments for localized edits. Finally, we propose a novel cross-attention regularization technique that penalizes unrelated cross-attention scores in the RoI during the denoising steps, ensuring localized edits. Our approach, without re-training and fine-tuning, consistently improves the performance of existing methods in various editing benchmarks.

Images produced by text-to-image diffusion models might not always faithfully represent the semantic intent of the provided text prompt, where the model might overlook or entirely fail to produce certain objects. Existing solutions often require customly tailored functions for each of these problems, leading to sub-optimal results, especially for complex prompts. Our work introduces a novel perspective by tackling this challenge in a contrastive context. Our approach intuitively promotes the segregation of objects in attention maps while also maintaining that pairs of related attributes are kept close to each other. We conduct extensive experiments across a wide variety of scenarios, each involving unique combinations of objects, attributes, and scenes. These experiments effectively showcase the versatility, efficiency, and flexibility of our method in working with both latent and pixel-based diffusion models, including Stable Diffusion and Imagen. Moreover, we publicly share our source code to facilitate further research.

Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage data augmentation approach that leverages NeRF's own view synthesis ability to address these limitations. With Re-Nerfing, we enhance the geometric consistency of novel views as follows: First, we train a NeRF with the available views. Then, we use the optimized NeRF to synthesize pseudo-views around the original ones with a view selection strategy to improve coverage and preserve view quality. Finally, we train a second NeRF with both the original images and the pseudo views masking out uncertain regions. Extensive experiments applying Re-Nerfing on various pipelines on the mip-NeRF 360 dataset, including Gaussian Splatting, provide valuable insights into the improvements achievable without external data or supervision, on denser and sparser input scenarios. Project page: https://renerfing.github.io, Comment: Code will be released upon acceptance

In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods often suffer from oversmoothed reconstructions, especially for complex real-world scenes. In this work, we introduce DNS SLAM, a novel neural RGB-D semantic SLAM approach featuring a hybrid representation. Relying only on 2D semantic priors, we propose the first semantic neural SLAM method that trains class-wise scene representations while providing stable camera tracking at the same time. Our method integrates multi-view geometry constraints with image-based feature extraction to improve appearance details and to output color, density, and semantic class information, enabling many downstream applications. To further enable real-time tracking, we introduce a lightweight coarse scene representation which is trained in a self-supervised manner in latent space. Our experimental results achieve state-of-the-art performance on both synthetic data and real-world data tracking while maintaining a commendable operational speed on off-the-shelf hardware. Further, our method outputs class-wise decomposed reconstructions with better texture capturing appearance and geometric details.

Reconstructing hand-held objects from a single RGB image is a challenging task in computer vision. In contrast to prior works that utilize deterministic modeling paradigms, we employ a point cloud denoising diffusion model to account for the probabilistic nature of this problem. In the core, we introduce centroid-fixed dual-stream conditional diffusion for monocular hand-held object reconstruction (D-SCo), tackling two predominant challenges. First, to avoid the object centroid from deviating, we utilize a novel hand-constrained centroid fixing paradigm, enhancing the stability of diffusion and reverse processes and the precision of feature projection. Second, we introduce a dual-stream denoiser to semantically and geometrically model hand-object interactions with a novel unified hand-object semantic embedding, enhancing the reconstruction performance of the hand-occluded region of the object. Experiments on the synthetic ObMan dataset and three real-world datasets HO3D, MOW and DexYCB demonstrate that our approach can surpass all other state-of-the-art methods. Codes will be released.

Neural Fields (NFs) have gained momentum as a tool for compressing various data modalities - e.g. images and videos. This work leverages previous advances and proposes a novel NF-based compression algorithm for 3D data. We derive two versions of our approach - one tailored to watertight shapes based on Signed Distance Fields (SDFs) and, more generally, one for arbitrary non-watertight shapes using Unsigned Distance Fields (UDFs). We demonstrate that our method excels at geometry compression on 3D point clouds as well as meshes. Moreover, we show that, due to the NF formulation, it is straightforward to extend our compression algorithm to compress both geometry and attribute (e.g. color) of 3D data.

Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin., Comment: CVPR 2024 accepted. Code is available at: https://github.com/NOrangeeroli/SecondPose

Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation, while also providing improvements on image-level tasks such as classification and retrieval. SILC models sets a new state of the art for zero-shot classification, few shot classification, image and text retrieval, zero-shot segmentation, and open vocabulary segmentation. We further show that SILC features greatly benefit open vocabulary detection, captioning and visual question answering.

Previous works concerning single-view hand-held object reconstruction typically rely on supervision from 3D ground-truth models, which are hard to collect in real world. In contrast, readily accessible hand-object videos offer a promising training data source, but they only give heavily occluded object observations. In this paper, we present a novel synthetic-to-real framework to exploit Multi-view Occlusion-aware supervision from hand-object videos for Hand-held Object reconstruction (MOHO) from a single image, tackling two predominant challenges in such setting: hand-induced occlusion and object's self-occlusion. First, in the synthetic pre-training stage, we render a large-scaled synthetic dataset SOMVideo with hand-object images and multi-view occlusion-free supervisions, adopted to address hand-induced occlusion in both 2D and 3D spaces. Second, in the real-world finetuning stage, MOHO leverages the amodal-mask-weighted geometric supervision to mitigate the unfaithful guidance caused by the hand-occluded supervising views in real world. Moreover, domain-consistent occlusion-aware features are amalgamated in MOHO to resist object's self-occlusion for inferring the complete object shape. Extensive experiments on HO3D and DexYCB datasets demonstrate 2D-supervised MOHO gains superior results against 3D-supervised methods by a large margin., Comment: CVPR 2024

This paper introduces a new benchmark dataset, Open-Structure, for evaluating visual odometry and SLAM methods, which directly equips point and line measurements, correspondences, structural associations, and co-visibility factor graphs instead of providing raw images. Based on the proposed benchmark dataset, these 2D or 3D data can be directly input to different stages of SLAM pipelines to avoid the impact of the data preprocessing modules in ablation experiments. First, we propose a dataset generator for real-world and simulated scenarios. In real-world scenes, it maintains the same observations and occlusions as actual feature extraction results. Those generated simulation sequences enhance the dataset's diversity by introducing various carefully designed trajectories and observations. Second, a SLAM baseline is proposed using our dataset to evaluate widely used modules in camera pose tracking, parametrization, and optimization modules. By evaluating these state-of-the-art algorithms across different scenarios, we discern each module's strengths and weaknesses within the camera tracking and optimization process. Our dataset and baseline are available at \url{https://github.com/yanyan-li/Open-Structure}.

Object rearrangement is pivotal in robotic-environment interactions, representing a significant capability in embodied AI. In this paper, we present SG-Bot, a novel rearrangement framework that utilizes a coarse-to-fine scheme with a scene graph as the scene representation. Unlike previous methods that rely on either known goal priors or zero-shot large models, SG-Bot exemplifies lightweight, real-time, and user-controllable characteristics, seamlessly blending the consideration of commonsense knowledge with automatic generation capabilities. SG-Bot employs a three-fold procedure--observation, imagination, and execution--to adeptly address the task. Initially, objects are discerned and extracted from a cluttered scene during the observation. These objects are first coarsely organized and depicted within a scene graph, guided by either commonsense or user-defined criteria. Then, this scene graph subsequently informs a generative model, which forms a fine-grained goal scene considering the shape information from the initial scene and object semantics. Finally, for execution, the initial and envisioned goal scenes are matched to formulate robotic action policies. Experimental results demonstrate that SG-Bot outperforms competitors by a large margin., Comment: ICRA 2024 accepted. Project website: https://sites.google.com/view/sg-bot

Reconstructing both objects and hands in 3D from a single RGB image is complex. Existing methods rely on manually defined hand-object constraints in Euclidean space, leading to suboptimal feature learning. Compared with Euclidean space, hyperbolic space better preserves the geometric properties of meshes thanks to its exponentially-growing space distance, which amplifies the differences between the features based on similarity. In this work, we propose the first precise hand-object reconstruction method in hyperbolic space, namely Dynamic Hyperbolic Attention Network (DHANet), which leverages intrinsic properties of hyperbolic space to learn representative features. Our method that projects mesh and image features into a unified hyperbolic space includes two modules, ie. dynamic hyperbolic graph convolution and image-attention hyperbolic graph convolution. With these two modules, our method learns mesh features with rich geometry-image multi-modal information and models better hand-object interaction. Our method provides a promising alternative for fine hand-object reconstruction in hyperbolic space. Extensive experiments on three public datasets demonstrate that our method outperforms most state-of-the-art methods., Comment: Accpeted by ICCV 2023

Continual Learning aims to learn a single model on a sequence of tasks without having access to data from previous tasks. The biggest challenge in the domain still remains catastrophic forgetting: a loss in performance on seen classes of earlier tasks. Some existing methods rely on an expensive replay buffer to store a chunk of data from previous tasks. This, while promising, becomes expensive when the number of tasks becomes large or data can not be stored for privacy reasons. As an alternative, prompt-based methods have been proposed that store the task information in a learnable prompt pool. This prompt pool instructs a frozen image encoder on how to solve each task. While the model faces a disjoint set of classes in each task in this setting, we argue that these classes can be encoded to the same embedding space of a pre-trained language encoder. In this work, we propose Language Guidance for Prompt-based Continual Learning (LGCL) as a plug-in for prompt-based methods. LGCL is model agnostic and introduces language guidance at the task level in the prompt pool and at the class level on the output feature of the vision encoder. We show with extensive experimentation that LGCL consistently improves the performance of prompt-based continual learning methods to set a new state-of-the art. LGCL achieves these performance improvements without needing any additional learnable parameters., Comment: Accepted at ICCV 2023

Since real-world training datasets cannot properly sample the long tail of the underlying data distribution, corner cases and rare out-of-domain samples can severely hinder the performance of state-of-the-art models. This problem becomes even more severe for dense tasks, such as 3D semantic segmentation, where points of non-standard objects can be confidently associated to the wrong class. In this work, we focus on improving the generalization to out-of-domain data. We achieve this by augmenting the training set with adversarial examples. First, we learn a set of vectors that deform the objects in an adversarial fashion. To prevent the adversarial examples from being too far from the existing data distribution, we preserve their plausibility through a series of constraints, ensuring sensor-awareness and shapes smoothness. Then, we perform adversarial augmentation by applying the learned sample-independent vectors to the available objects when training a model. We conduct extensive experiments across a variety of scenarios on data from KITTI, Waymo, and CrashD for 3D object detection, and on data from SemanticKITTI, Waymo, and nuScenes for 3D semantic segmentation. Despite training on a standard single dataset, our approach substantially improves the robustness and generalization of both 3D object detection and 3D semantic segmentation methods to out-of-domain data., Comment: 37 pages, 12 figures

While state-of-the-art monocular depth estimation approaches achieve impressive results in ideal settings, they are highly unreliable under challenging illumination and weather conditions, such as at nighttime or in the presence of rain. In this paper, we uncover these safety-critical issues and tackle them with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions, as well as for different types of learning supervision. We achieve this by exploiting the efficacy of existing methods under perfect settings. Therefore, we provide valid training signals independently of what is in the input. First, we generate a set of complex samples corresponding to the normal training ones. Then, we train the model by guiding its self- or full-supervision by feeding the generated samples and computing the standard losses on the corresponding original images. Doing so enables a single model to recover information across diverse conditions without modifications at inference time. Extensive experiments on two challenging public datasets, namely nuScenes and Oxford RobotCar, demonstrate the effectiveness of our techniques, outperforming prior works by a large margin in both standard and challenging conditions. Source code and data are available at: https://md4all.github.io., Comment: ICCV 2023. Source code and data: https://md4all.github.io

Reconstructing hand-held objects from a single RGB image is an important and challenging problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions, since SDF is only reliable within the proximity of the target, and hence, infeasible to simultaneously encode local hand and object cues. To address this issue, we propose DDF-HO, a novel approach leveraging Directed Distance Field (DDF) as the shape representation. Unlike SDF, DDF maps a ray in 3D space, consisting of an origin and a direction, to corresponding DDF values, including a binary visibility signal determining whether the ray intersects the objects and a distance value measuring the distance from origin to target in the given direction. We randomly sample multiple rays and collect local to global geometric features for them by introducing a novel 2D ray-based feature aggregation scheme and a 3D intersection-aware hand pose embedding, combining 2D-3D features to model hand-object interactions. Extensive experiments on synthetic and real-world datasets demonstrate that DDF-HO consistently outperforms all baseline methods by a large margin, especially under Chamfer Distance, with about 80% leap forward. Codes are available at https://github.com/ZhangCYG/DDFHO., Comment: Camera Ready for NeurIPS 2023

In this paper, we present a novel shape reconstruction method leveraging diffusion model to generate 3D sparse point cloud for the object captured in a single RGB image. Recent methods typically leverage global embedding or local projection-based features as the condition to guide the diffusion model. However, such strategies fail to consistently align the denoised point cloud with the given image, leading to unstable conditioning and inferior performance. In this paper, we present CCD-3DR, which exploits a novel centered diffusion probabilistic model for consistent local feature conditioning. We constrain the noise and sampled point cloud from the diffusion model into a subspace where the point cloud center remains unchanged during the forward diffusion process and reverse process. The stable point cloud center further serves as an anchor to align each point with its corresponding local projection-based features. Extensive experiments on synthetic benchmark ShapeNet-R2N2 demonstrate that CCD-3DR outperforms all competitors by a large margin, with over 40% improvement. We also provide results on real-world dataset Pix3D to thoroughly demonstrate the potential of CCD-3DR in real-world applications. Codes will be released soon, Comment: 11 pages

In this paper, we propose U-RED, an Unsupervised shape REtrieval and Deformation pipeline that takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD models from a pre-established database to tightly match the target. Considering existing methods typically fail to handle noisy partial observations, U-RED is designed to address this issue from two aspects. First, since one partial shape may correspond to multiple potential full shapes, the retrieval method must allow such an ambiguous one-to-many relationship. Thereby U-RED learns to project all possible full shapes of a partial target onto the surface of a unit sphere. Then during inference, each sampling on the sphere will yield a feasible retrieval. Second, since real-world partial observations usually contain noticeable noise, a reliable learned metric that measures the similarity between shapes is necessary for stable retrieval. In U-RED, we design a novel point-wise residual-guided metric that allows noise-robust comparison. Extensive experiments on the synthetic datasets PartNet, ComplementMe and the real-world dataset Scan2CAD demonstrate that U-RED surpasses existing state-of-the-art approaches by 47.3%, 16.7% and 31.6% respectively under Chamfer Distance., Comment: ICCV2023