Search

Recently, many 2D pretrained foundational models have demonstrated impressive zero-shot prediction capabilities. In this work, we design a novel pipeline for zero-shot 3D part segmentation, called ZeroPS. It high-quality transfers knowledge from 2D pretrained foundational models to 3D point clouds. The main idea of our approach is to explore the natural relationship between multi-view correspondences and the prompt mechanism of foundational models and build bridges on it. Our pipeline consists of two components: 1) a self-extension component that extends 2D groups from a single viewpoint to spatial global-level 3D groups; 2) a multi-modal labeling component that introduces a two-dimensional checking mechanism to vote each 2D predicted bounding box to the best matching 3D part, and a Class Non-highest Vote Penalty function to refine the Vote Matrix. Additionally, a merging algorithm is included to merge part-level 3D groups. Extensive evaluation of three zero-shot segmentation tasks on PartnetE datasets, achieving state-of-the-art results with significant improvements (+19.6%, +5.2% and +4.9%, respectively) over existing methods. Our proposed approach does not need any training, fine-tuning or learnable parameters. It is hardly affected by domain shift. The code will be released., Comment: 11 pages, 6 figures; references added

Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages. The main challenges are the domain gaps between the CAD models and the real scene's objects, including model-to-scene (from a single model to the scene) and synthetic-to-real (from synthetic model to real scene's object). To handle the above challenges, Model2Scene first simulates a crowded scene by mixing data-augmented CAD models. Next, we propose a novel feature regularization operation, termed Deep Convex-hull Regularization (DCR), to project point features into a unified convex hull space, reducing the domain gap. Ultimately, we impose contrastive loss on language embedding and the point features of CAD models to pre-train the 3D network. Extensive experiments verify the learned 3D scene representation is beneficial for various downstream tasks, including label-free 3D object salient detection, label-efficient 3D scene perception and zero-shot 3D semantic segmentation. Notably, Model2Scene yields impressive label-free 3D object salient detection with an average mAP of 46.08\% and 55.49\% on the ScanNet and S3DIS datasets, respectively. The code will be publicly available., Comment: arXiv admin note: substantial text overlap with arXiv:2203.10546

Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of CLIP and SAM for label-free scene understanding has yet to be explored. In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. The primary challenge lies in effectively supervising networks under extremely noisy pseudo labels, which are generated by CLIP and further exacerbated during the propagation from the 2D to the 3D domain. To tackle these challenges, we propose a novel Cross-modality Noisy Supervision (CNS) method that leverages the strengths of CLIP and SAM to supervise 2D and 3D networks simultaneously. In particular, we introduce a prediction consistency regularization to co-train 2D and 3D networks, then further impose the networks' latent space consistency using the SAM's robust feature representation. Experiments conducted on diverse indoor and outdoor datasets demonstrate the superior performance of our method in understanding 2D and 3D open environments. Our 2D and 3D network achieves label-free semantic segmentation with 28.4\% and 33.5\% mIoU on ScanNet, improving 4.7\% and 7.9\%, respectively. For nuImages and nuScenes datasets, the performance is 22.1\% and 26.8\% with improvements of 3.5\% and 6.0\%, respectively. Code is available. (https://github.com/runnanchen/Label-Free-Scene-Understanding)., Comment: NeurIPS 2023

We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However, previous methods neglect the fine-grained relationship between the language and the 3D geometric elements. To this end, we propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects and employ a fine-grained alignment between language and the learned geometric primitives. Therefore, guided by language, the network recognizes the novel objects represented with geometric primitives. Specifically, we formulate a novel point visual representation, the similarity vector of the point's feature to the learnable prototypes, where the prototypes automatically encode geometric primitives via back-propagation. Besides, we propose a novel Unknown-aware InfoNCE Loss to fine-grained align the visual representation with language. Extensive experiments show that our method significantly outperforms other state-of-the-art methods in the harmonic mean-intersection-over-union (hIoU), with the improvement of 17.8\%, 30.4\%, 9.2\% and 7.9\% on S3DIS, ScanNet, SemanticKITTI and nuScenes datasets, respectively. Codes are available (https://github.com/runnanchen/Zero-Shot-Point-Cloud-Segmentation), Comment: ACM MM 2023

Creating 3D shapes from 2D drawings is an important problem with applications in content creation for computer animation and virtual reality. We introduce a new sketch-based system, CreatureShop, that enables amateurs to create high-quality textured 3D character models from 2D drawings with ease and efficiency. CreatureShop takes an input bitmap drawing of a character (such as an animal or other creature), depicted from an arbitrary descriptive pose and viewpoint, and creates a 3D shape with plausible geometric details and textures from a small number of user annotations on the 2D drawing. Our key contributions are a novel oblique view modeling method, a set of systematic approaches for producing plausible textures on the invisible or occluded parts of the 3D character (as viewed from the direction of the input drawing), and a user-friendly interactive system. We validate our system and methods by creating numerous 3D characters from various drawings, and compare our results with related works to show the advantages of our method. We perform a user study to evaluate the usability of our system, which demonstrates that our system is a practical and efficient approach to create fully-textured 3D character models for novice users., Comment: This is the author's version of the article published in IEEE Transactions on Visualization and Computer Graphics, 2022

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the InfoNCE loss accordingly. We show that our learned image representations are general. By fine-tuning our pre-trained representations for various 2D image-based downstream tasks, including semantic segmentation, object detection, and instance segmentation on real-world indoor scene datasets, we achieve superior performance compared with state-of-the-art methods., Comment: Accepted by CVPR 2022

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the real scene annotation burden, i.e., taking the labelled 3D synthetic models as reference for supervision, the neural network aims to recognize specific categories of objects on a real scene scan (without scene annotation for supervision). The problem studies how to transfer knowledge from synthetic 3D models to real 3D scenes and is named Referring Transfer Learning (RTL). The main challenge is solving the model-to-scene (from a single model to the scene) and synthetic-to-real (from synthetic model to real scene's object) gap between the synthetic model and the real scene. To this end, we propose a simple yet effective framework to perform two alignment operations. First, physical data alignment aims to make the synthetic models cover the diversity of the scene's objects with data processing techniques. Then a novel \textbf{convex-hull regularized feature alignment} introduces learnable prototypes to project the point features of both synthetic models and real scenes to a unified feature space, which alleviates the domain gap. These operations ease the model-to-scene and synthetic-to-real difficulty for a network to recognize the target objects on a real unseen scene. Experiments show that our method achieves the average mAP of 46.08\% and 55.49\% on the ScanNet and S3DIS datasets by learning the synthetic models from the ModelNet dataset. Code will be publicly available.

Personalized video highlight detection aims to shorten a long video to interesting moments according to a user's preference, which has recently raised the community's attention. Current methods regard the user's history as holistic information to predict the user's preference but negating the inherent diversity of the user's interests, resulting in vague preference representation. In this paper, we propose a simple yet efficient preference reasoning framework (PR-Net) to explicitly take the diverse interests into account for frame-level highlight prediction. Specifically, distinct user-specific preferences for each input query frame are produced, presented as the similarity weighted sum of history highlights to the corresponding query frame. Next, distinct comprehensive preferences are formed by the user-specific preferences and a learnable generic preference for more overall highlight measurement. Lastly, the degree of highlight and non-highlight for each query frame is calculated as semantic similarity to its comprehensive and non-highlight preferences, respectively. Besides, to alleviate the ambiguity due to the incomplete annotation, a new bi-directional contrastive loss is proposed to ensure a compact and differentiable metric space. In this way, our method significantly outperforms state-of-the-art methods with a relative improvement of 12% in mean accuracy precision., Comment: ICCV 2021

We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in the image. This task is challenging due to the lack of explicit fine-grained region word alignments as supervision. Previous weakly supervised methods mainly explore various kinds of regularization schemes to improve attention accuracy. However, their performances are still far from the fully supervised ones. One main issue that has been ignored is that the attention for generating visually groundable words may only focus on the most discriminate parts and can not cover the whole object. To this end, we propose a simple yet effective method to alleviate the issue, termed as partial grounding problem in our paper. Specifically, we design a distributed attention mechanism to enforce the network to aggregate information from multiple spatially different regions with consistent semantics while generating the words. Therefore, the union of the focused region proposals should form a visual region that encloses the object of interest completely. Extensive experiments have demonstrated the superiority of our proposed method compared with the state-of-the-arts., Comment: mm21

Detecting 3D landmarks on cone-beam computed tomography (CBCT) is crucial to assessing and quantifying the anatomical abnormalities in 3D cephalometric analysis. However, the current methods are time-consuming and suffer from large biases in landmark localization, leading to unreliable diagnosis results. In this work, we propose a novel Structure-Aware Long Short-Term Memory framework (SA-LSTM) for efficient and accurate 3D landmark detection. To reduce the computational burden, SA-LSTM is designed in two stages. It first locates the coarse landmarks via heatmap regression on a down-sampled CBCT volume and then progressively refines landmarks by attentive offset regression using multi-resolution cropped patches. To boost accuracy, SA-LSTM captures global-local dependence among the cropping patches via self-attention. Specifically, a novel graph attention module implicitly encodes the landmark's global structure to rationalize the predicted position. Moreover, a novel attention-gated module recursively filters irrelevant local features and maintains high-confident local predictions for aggregating the final result. Experiments conducted on an in-house dataset and a public dataset show that our method outperforms state-of-the-art methods, achieving 1.64 mm and 2.37 mm average errors, respectively. Furthermore, our method is very efficient, taking only 0.5 seconds for inferring the whole CBCT volume of resolution 768$\times$768$\times$576., Comment: IEEE Transactions on medical images

We introduce CurveFusion, the first approach for high quality scanning of thin structures at interactive rates using a handheld RGBD camera. Thin filament-like structures are mathematically just 1D curves embedded in R^3, and integration-based reconstruction works best when depth sequences (from the thin structure parts) are fused using the object's (unknown) curve skeleton. Thus, using the complementary but noisy color and depth channels, CurveFusion first automatically identifies point samples on potential thin structures and groups them into bundles, each being a group of a fixed number of aligned consecutive frames. Then, the algorithm extracts per-bundle skeleton curves using L1 axes, and aligns and iteratively merges the L1 segments from all the bundles to form the final complete curve skeleton. Thus, unlike previous methods, reconstruction happens via integration along a data-dependent fusion primitive, i.e., the extracted curve skeleton. We extensively evaluate CurveFusion on a range of challenging examples, different scanner and calibration settings, and present high fidelity thin structure reconstructions previously just not possible from raw RGBD sequences.

Well-annotated medical images are costly and sometimes even impossible to acquire, hindering landmark detection accuracy to some extent. Semi-supervised learning alleviates the reliance on large-scale annotated data by exploiting the unlabeled data to understand the population structure of anatomical landmarks. The global shape constraint is the inherent property of anatomical landmarks that provides valuable guidance for more consistent pseudo labelling of the unlabeled data, which is ignored in the previously semi-supervised methods. In this paper, we propose a model-agnostic shape-regulated self-training framework for semi-supervised landmark detection by fully considering the global shape constraint. Specifically, to ensure pseudo labels are reliable and consistent, a PCA-based shape model adjusts pseudo labels and eliminate abnormal ones. A novel Region Attention loss to make the network automatically focus on the structure consistent regions around pseudo labels. Extensive experiments show that our approach outperforms other semi-supervised methods and achieves notable improvement on three medical image datasets. Moreover, our framework is flexible and can be used as a plug-and-play module integrated into most supervised methods to improve performance further., Comment: Accepted to Neurocomputing

We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures. Extensive evaluations and comparisons show our method has superior performance and robustness. The learned skeletal representation will benefit several unsupervised tasks for point clouds, such as surface reconstruction and segmentation., Comment: Accepted to CVPR2021 (oral). Project: https://github.com/clinplayer/Point2Skeleton

We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category based on the cycle-consistency formulation. In order to learn discriminative pointwise features from point cloud data, we incorporate in the formulation a regularization term based on Sinkhorn normalization to enhance the learned pointwise mappings to be as bijective as possible. Besides, a random rigid transform of the source shape is introduced to form a triplet cycle to improve the model's robustness against perturbations. Comprehensive experiments demonstrate that the learned pointwise features through our framework benefits various point cloud analysis tasks, e.g. partial shape registration and keypoint transfer. We also show that the learned pointwise features can be leveraged by supervised methods to improve the part segmentation performance with either the full training dataset or just a small portion of it., Comment: Accepted to ECCV2020

Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera. Specifically, we present a new curve-based approach to estimate accurate camera poses by establishing correspondences between featureless thin objects in the foreground in consecutive video frames, without requiring visual texture in the background scene to lock on. Enabled by this effective curve-based camera pose estimation strategy, we develop an iterative optimization method with tailored measures on geometry, topology as well as self-occlusion handling for reconstructing 3D thin structures. Extensive validations on a variety of thin structures show that our method achieves accurate camera pose estimation and faithful reconstruction of 3D thin structures with complex shape and topology at a level that has not been attained by other existing reconstruction methods., Comment: Accepted by SIGGRAPH 2020

Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points produced by our method encode the shape structure intrinsically and exhibit semantic consistency across all the shape instances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves comparable performance with the state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints, Comment: Accepted by CVPR 2020

Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels of resolution and semantics. Based on this observation, we propose a novel attentive feature pyramid fusion module (AFPF) to explicitly shape high-resolution and semantically enhanced fusion features to achieve significantly higher accuracy than existing deep learning-based methods. We also combine heat maps and offset maps to perform pixel-wise regression-voting to improve detection accuracy. By incorporating the AFPF and regression-voting, we develop an end-to-end deep learning framework that improves detection accuracy by 7%~11% for all the evaluation metrics over the state-of-the-art method. We present ablation studies to give more insights into different components of our method and demonstrate its generalization capability and stability for unseen data from diverse devices., Comment: Early accepted by International Conference on Medical image computing and computer-assisted intervention (MICCAI 2019)