Search

We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at a point by aggregating nearby tokens, where fast approximate neighbors can be retrieved thanks to the serialization. We serialize the point cloud at different levels/scales, and non-linearly aggregate a feature to predict the SDF value. We show that aggregating across multiple scales is critical to overcome the approximations introduced by the serialization (i.e. false negatives in the neighborhood). Our frameworks sets the new state-of-the-art in terms of accuracy and efficiency (better or similar performance with half the latency of the best prior method, coupled with a simpler implementation), particularly on outdoor datasets where sparse-grid methods have shown limited performance., Comment: Project page: see https://theialab.github.io/noksr/

Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of radiance fields in favor of rasterization. This has yielded a significant improvement in rendering speeds due to the efficiency of rasterization algorithms and hardware, but has come at a cost: the approximations that make rasterization efficient also make implementation of light transport phenomena like reflection and refraction much more difficult. We propose a novel scene representation which avoids these approximations, but keeps the efficiency and reconstruction quality of splatting by leveraging a decades-old efficient volumetric mesh ray tracing algorithm which has been largely overlooked in recent computer vision research. The resulting model, which we name Radiant Foam, achieves rendering speed and quality comparable to Gaussian Splatting, without the constraints of rasterization. Unlike ray traced Gaussian models that use hardware ray tracing acceleration, our method requires no special hardware or APIs beyond the standard features of a programmable GPU.

In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination with masked image modeling, their gains have been marginal when it comes to recognition tasks. We thus investigate why this would be the case, in an attempt to find effective ways to combine the two ideas. Specifically, we find three critical conditions: corruption and restoration must be applied within the encoder, noise must be introduced in the feature space, and an explicit disentanglement between noised and masked tokens is necessary. By implementing these findings, we demonstrate improved pre-training performance for a wide range of recognition tasks, including those that require fine-grained, high-frequency information to solve.

To efficiently adapt large models or to train generative models of neural representations, Hypernetworks have drawn interest. While hypernetworks work well, training them is cumbersome, and often requires ground truth optimized weights for each sample. However, obtaining each of these weights is a training problem of its own-one needs to train, e.g., adaptation weights or even an entire neural field for hypernetworks to regress to. In this work, we propose a method to train hypernetworks, without the need for any per-sample ground truth. Our key idea is to learn a Hypernetwork `Field` and estimate the entire trajectory of network weight training instead of simply its converged state. In other words, we introduce an additional input to the Hypernetwork, the convergence state, which then makes it act as a neural field that models the entire convergence pathway of a task network. A critical benefit in doing so is that the gradient of the estimated weights at any convergence state must then match the gradients of the original task -- this constraint alone is sufficient to train the Hypernetwork Field. We demonstrate the effectiveness of our method through the task of personalized image generation and 3D shape reconstruction from images and point clouds, demonstrating competitive results without any per-sample ground truth.

We introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the disk structures in the form of two-dimensional density and velocity maps, and outputs disk and planet properties, that is, the Shakura--Sunyaev viscosity, the disk aspect ratio, the planet--star mass ratio, and the planet's radius and azimuth. We integrate the Covariance Matrix Adaptation Evolution Strategy (CMA--ES), an evolutionary algorithm tailored for complex optimization problems, and the Protoplanetary Disk Operator Network (PPDONet), a neural network designed to predict solutions of disk--planet interactions. Our tool is fully automated and can retrieve parameters in one system in three minutes on an Nvidia A100 graphics processing unit. We empirically demonstrate that our tool achieves percent-level or higher accuracy, and is able to handle missing data and unknown levels of noise., Comment: Accepted to ApJ

We present a method for reconstructing a clear Neural Radiance Field (NeRF) even with fast camera motions. To address blur artifacts, we leverage both (blurry) RGB images and event camera data captured in a binocular configuration. Importantly, when reconstructing our clear NeRF, we consider the camera modeling imperfections that arise from the simple pinhole camera model as learned embeddings for each camera measurement, and further learn a mapper that connects event camera measurements with RGB data. As no previous dataset exists for our binocular setting, we introduce an event camera dataset with captures from a 3D-printed stereo configuration between RGB and event cameras. Empirically, we evaluate our introduced dataset and EVIMOv2 and show that our method leads to improved reconstructions. Our code and dataset are available at https://github.com/ubc-vision/LSENeRF.

Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parametric representations. While implicits are well suited for tasks such as in-out queries, they lack natural 2D parameterization, complicating tasks such as texture or normal mapping. Conversely, parametric representations support the latter tasks but are ill-suited for occupancy queries. We propose a novel learned alternative to these approaches, based on intersections of localized explicit, or height-field, surfaces. Since explicits can be trivially expressed both implicitly and parametrically, NESI directly supports a wider range of processing operations than implicit alternatives, including occupancy queries and parametric access. We represent input shapes using a collection of differently oriented height-field bounded half-spaces combined using volumetric Boolean intersections. We first tightly bound each input using a pair of oppositely oriented height-fields, forming a Double Height-Field (DHF) Hull. We refine this hull by intersecting it with additional localized height-fields (HFs) that capture surface regions in its interior. We minimize the number of HFs necessary to accurately capture each input and compactly encode both the DHF hull and the local HFs as neural functions defined over subdomains of R^2. This reduced dimensionality encoding delivers high-quality compact approximations. Given similar parameter count, or storage capacity, NESI significantly reduces approximation error compared to the state of the art, especially at lower parameter counts.

We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality., Comment: Project page: https://theialab.github.io/laghashes/

Largely due to their implicit nature, neural fields lack a direct mechanism for filtering, as Fourier analysis from discrete signal processing is not directly applicable to these representations. Effective filtering of neural fields is critical to enable level-of-detail processing in downstream applications, and support operations that involve sampling the field on regular grids (e.g. marching cubes). Existing methods that attempt to decompose neural fields in the frequency domain either resort to heuristics or require extensive modifications to the neural field architecture. We show that via a simple modification, one can obtain neural fields that are low-pass filtered, and in turn show how this can be exploited to obtain a frequency decomposition of the entire signal. We demonstrate the validity of our technique by investigating level-of-detail reconstruction, and showing how coarser representations can be computed effectively., Comment: Project Page: https://theialab.github.io/banf

3D Gaussian Splatting has recently been embraced as a versatile and effective method for scene reconstruction and novel view synthesis, owing to its high-quality results and compatibility with hardware rasterization. Despite its advantages, Gaussian Splatting's reliance on high-quality point cloud initialization by Structure-from-Motion (SFM) algorithms is a significant limitation to be overcome. To this end, we investigate various initialization strategies for Gaussian Splatting and delve into how volumetric reconstructions from Neural Radiance Fields (NeRF) can be utilized to bypass the dependency on SFM data. Our findings demonstrate that random initialization can perform much better if carefully designed and that by employing a combination of improved initialization strategies and structure distillation from low-cost NeRF models, it is possible to achieve equivalent results, or at times even superior, to those obtained from SFM initialization. Source code is available at https://theialab.github.io/nerf-3dgs .

While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which can lead to poor-quality renderings, and reliance on a good initialization. In this work, we rethink the set of 3D Gaussians as a random sample drawn from an underlying probability distribution describing the physical representation of the scene-in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates can be converted as Stochastic Gradient Langevin Dynamics (SGLD) updates by simply introducing noise. We then rewrite the densification and pruning strategies in 3D Gaussian Splatting as simply a deterministic state transition of MCMC samples, removing these heuristics from the framework. To do so, we revise the 'cloning' of Gaussians into a relocalization scheme that approximately preserves sample probability. To encourage efficient use of Gaussians, we introduce a regularizer that promotes the removal of unused Gaussians. On various standard evaluation scenes, we show that our method provides improved rendering quality, easy control over the number of Gaussians, and robustness to initialization.

In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience. Our method provides robustness against variations in masking ratios, effectively mitigating the performance instability issues common in existing methods. This relaxes the sensitivity of MIM-based pre-training to masking ratios, which in turn allows us to propose an adaptive strategy for `tailored' masking ratios for each data sample, which no existing method can provide. Toward this goal, we propose an Adaptive Masking Ratio (AMR) strategy that dynamically adjusts the proportion of masking for the unique content of each image based on token salience. We show that our method significantly improves over the state-of-the-art in mask-based pre-training on the ImageNet-1K dataset.

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt engineering, current approaches largely rely on embedding inversion by optimizing and then mapping them to pseudo-tokens. However, working with such high-dimensional vector representations is challenging because they lack semantics and interpretability, and only allow simple vector operations when using them. Instead, this work focuses on inverting the diffusion model to obtain interpretable language prompts directly. The challenge of doing this lies in the fact that the resulting optimization problem is fundamentally discrete and the space of prompts is exponentially large; this makes using standard optimization techniques, such as stochastic gradient descent, difficult. To this end, we utilize a delayed projection scheme to optimize for prompts representative of the vocabulary space in the model. Further, we leverage the findings that different timesteps of the diffusion process cater to different levels of detail in an image. The later, noisy, timesteps of the forward diffusion process correspond to the semantic information, and therefore, prompt inversion in this range provides tokens representative of the image semantics. We show that our approach can identify semantically interpretable and meaningful prompts for a target image which can be used to synthesize diverse images with similar content. We further illustrate the application of the optimized prompts in evolutionary image generation and concept removal.

We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations while achieving the performance of recent fully supervised approaches. Our core idea is to propagate the scene-level labels to each point in the point cloud by creating pseudo labels in a conservative way. Specifically, we over-segment point cloud features via unsupervised clustering and associate scene-level labels with clusters through bipartite matching, thus propagating scene labels only to the most relevant clusters, leaving the rest to be guided solely via unsupervised clustering. We empirically demonstrate that over-segmentation and bipartite assignment plays a crucial role. We evaluate our method on ScanNet and S3DIS datasets, outperforming state of the art, and demonstrate that we can achieve results comparable to fully supervised methods., Comment: The first two authors contributed equally; Project website: https://densify-your-labels.github.io/

Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods based on point clouds do exist, but they do not perform well when the point cloud quality is low -- e.g., sparse or incomplete, which is often the case with real-world data. We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions. To deal with point cloud sparsity, we average across multiple scale levels -- but only among those that are valid, i.e., that have enough neighboring points in proximity to the ray of a pixel. To help model areas without points, we add a global voxel at the coarsest scale, thus unifying ``classical'' and point-based NeRF formulations. We validate our method on the NeRF Synthetic, ScanNet, and KITTI-360 datasets, outperforming the state of the art, with a significant gap compared to other NeRF-based methods, especially on more challenging scenes., Comment: Project website: https://pointnerfpp.github.io/

Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent methods for view synthesis based on diffusion have shown great progress, achieving consistency among various view estimates and at the same time abiding by the desired camera pose remains a critical problem yet to be solved. In this work, we demonstrate a strikingly simple method, where we utilize a pre-trained video diffusion model to solve this problem. Our key idea is that synthesizing a novel view could be reformulated as synthesizing a video of a camera going around the object of interest -- a scanning video -- which then allows us to leverage the powerful priors that a video diffusion model would have learned. Thus, to perform novel-view synthesis, we create a smooth camera trajectory to the target view that we wish to render, and denoise using both a view-conditioned diffusion model and a video diffusion model. By doing so, we obtain a highly consistent novel view synthesis, outperforming the state of the art., Comment: Project page: https://jgkwak95.github.io/ViVid-1-to-3/

We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that enables fast inference by utilizing textured polygons. Despite the high-quality novel view rendering that NeRF provides, a critical limitation is that it relies on volume rendering that can be computationally expensive and does not utilize the advancements in modern graphics hardware. Many existing methods fall short when it comes to modelling volumetric effects as they rely purely on surface rendering. We thus propose to model the scene with polygons, which can then be used to obtain the quadrature points required to model volumetric effects, and also their opacity and colour from the texture. To obtain such polygonal mesh, we train a specialized field whose zero-crossings would correspond to the quadrature points when volume rendering, and perform marching cubes on this field. We then perform ray-tracing and utilize the ray-tracing shader to obtain the final colour image. Our method allows an easy integration with existing graphics frameworks allowing rendering speed of over 100 frames-per-second for a $1920\times1080$ image, while still being able to represent non-opaque objects.

We present an approach to accelerate Neural Field training by efficiently selecting sampling locations. While Neural Fields have recently become popular, it is often trained by uniformly sampling the training domain, or through handcrafted heuristics. We show that improved convergence and final training quality can be achieved by a soft mining technique based on importance sampling: rather than either considering or ignoring a pixel completely, we weigh the corresponding loss by a scalar. To implement our idea we use Langevin Monte-Carlo sampling. We show that by doing so, regions with higher error are being selected more frequently, leading to more than 2x improvement in convergence speed. The code and related resources for this study are publicly available at https://ubc-vision.github.io/nf-soft-mining/.

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We leverage the emergent knowledge within text-to-image diffusion models, towards more robust unsupervised keypoints. Our core idea is to find text embeddings that would cause the generative model to consistently attend to compact regions in images (i.e. keypoints). To do so, we simply optimize the text embedding such that the cross-attention maps within the denoising network are localized as Gaussians with small standard deviations. We validate our performance on multiple datasets: the CelebA, CUB-200-2011, Tai-Chi-HD, DeepFashion, and Human3.6m datasets. We achieve significantly improved accuracy, sometimes even outperforming supervised ones, particularly for data that is non-aligned and less curated. Our code is publicly available and can be found through our project page: https://ubc-vision.github.io/StableKeypoints/

We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip. Our method is inspired by the recent work on Layered Neural Atlas (LNA). LNA, however, suffers from two major drawbacks: (1) the method is too slow for interactive editing, and (2) it offers insufficient support for some editing use cases, including direct frame editing and rigid texture tracking. To address these challenges we leverage and adopt highly efficient network architectures, powered by hash-grids encoding, to substantially improve processing speed. In addition, we learn bi-directional functions between image-atlas and introduce vectorized editing, which collectively enables a much greater variety of edits in both the atlas and the frames directly. Compared to LNA, our INVE reduces the learning and inference time by a factor of 5, and supports various video editing operations that LNA cannot. We showcase the superiority of INVE over LNA in interactive video editing through a comprehensive quantitative and qualitative analysis, highlighting its numerous advantages and improved performance. For video results, please see https://gabriel-huang.github.io/inve/

A relatively new concern for the forthcoming massive spectroscopic sky surveys is the impact of contamination from low earth orbit satellites. Several hundred thousand of these satellites are licensed for launch in the next few years and it has been estimated that, in some cases, up to a few percent of spectra could be contaminated when using wide field, multi-fiber spectrographs. In this paper, a multi-staged approach is used to assess the practicality and limitations of identifying and minimizing the impact of satellite contamination in a WEAVE-like stellar spectral survey. We develop a series of convolutional-network based architectures to attempt identification, stellar parameter and chemical abundances recovery, and source separation of stellar spectra that we artificially contaminate with satellite (i.e. solar-like) spectra. Our results show that we are able to flag 67% of all contaminated sources at a precision level of 80% for low-resolution spectra and 96% for high-resolution spectra. Additionally, we are able to remove the contamination from the spectra and recover the clean spectra with a $<$1% reconstruction error. The errors in stellar parameter predictions reduce by up to a factor of 2-3 when either including contamination as an augmentation to a training set or by removing the contamination from the spectra, with overall better performance in the former case. The presented methods illustrate several machine learning mitigation strategies that can be implemented to improve stellar parameters for contaminated spectra in the WEAVE stellar spectroscopic survey and others like it., Comment: 15 pages. To be published in MNRAS

Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences - locations in multiple images that have the same semantic meaning. Specifically, given an image, we optimize the prompt embeddings of these models for maximum attention on the regions of interest. These optimized embeddings capture semantic information about the location, which can then be transferred to another image. By doing so we obtain results on par with the strongly supervised state of the art on the PF-Willow dataset and significantly outperform (20.9% relative for the SPair-71k dataset) any existing weakly or unsupervised method on PF-Willow, CUB-200 and SPair-71k datasets., Comment: Project website: https://github.com/ubc-vision/LDM_correspondences

We develop a tool, which we name Protoplanetary Disk Operator Network (PPDONet), that can predict the solution of disk-planet interactions in protoplanetary disks in real-time. We base our tool on Deep Operator Networks (DeepONets), a class of neural networks capable of learning non-linear operators to represent deterministic and stochastic differential equations. With PPDONet we map three scalar parameters in a disk-planet system -- the Shakura \& Sunyaev viscosity $\alpha$, the disk aspect ratio $h_\mathrm{0}$, and the planet-star mass ratio $q$ -- to steady-state solutions of the disk surface density, radial velocity, and azimuthal velocity. We demonstrate the accuracy of the PPDONet solutions using a comprehensive set of tests. Our tool is able to predict the outcome of disk-planet interaction for one system in less than a second on a laptop. A public implementation of PPDONet is available at \url{https://github.com/smao-astro/PPDONet}., Comment: 10 pages, 6 figures, 2 tables; ApJL accepted

Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance. Existing methods are either data-driven, requiring an extensive corpus of data not publicly accessible to the research community, or fail to capture fine details because they rely on geometric face models that cannot represent fine-grained details in texture with a mesh discretization and linear deformation designed to model only a coarse face geometry. We introduce a method that bridges this gap by drawing inspiration from traditional computer graphics techniques. Unseen expressions are modeled by blending appearance from a sparse set of extreme poses. This blending is performed by measuring local volumetric changes in those expressions and locally reproducing their appearance whenever a similar expression is performed at test time. We show that our method generalizes to unseen expressions, adding fine-grained effects on top of smooth volumetric deformations of a face, and demonstrate how it generalizes beyond faces., Comment: Accepted to CVPR 2023. Project page: https://blendfields.github.io/

We propose a novel method that renders point clouds as if they are surfaces. The proposed method is differentiable and requires no scene-specific optimization. This unique capability enables, out-of-the-box, surface normal estimation, rendering room-scale point clouds, inverse rendering, and ray tracing with global illumination. Unlike existing work that focuses on converting point clouds to other representations--e.g., surfaces or implicit functions--our key idea is to directly infer the intersection of a light ray with the underlying surface represented by the given point cloud. Specifically, we train a set transformer that, given a small number of local neighbor points along a light ray, provides the intersection point, the surface normal, and the material blending weights, which are used to render the outcome of this light ray. Localizing the problem into small neighborhoods enables us to train a model with only 48 meshes and apply it to unseen point clouds. Our model achieves higher estimation accuracy than state-of-the-art surface reconstruction and point-cloud rendering methods on three test sets. When applied to room-scale point clouds, without any scene-specific optimization, the model achieves competitive quality with the state-of-the-art novel-view rendering methods. Moreover, we demonstrate ability to render and manipulate Lidar-scanned point clouds such as lighting control and object insertion., Comment: CVPR 2023

We introduce CN-DHF (Compact Neural Double-Height-Field), a novel hybrid neural implicit 3D shape representation that is dramatically more compact than the current state of the art. Our representation leverages Double-Height-Field (DHF) geometries, defined as closed shapes bounded by a pair of oppositely oriented height-fields that share a common axis, and leverages the following key observations: DHFs can be compactly encoded as 2D neural implicits that capture the maximal and minimal heights along the DHF axis; and typical closed 3D shapes are well represented as intersections of a very small number (three or fewer) of DHFs. We represent input geometries as CNDHFs by first computing the set of DHFs whose intersection well approximates each input shape, and then encoding these DHFs via neural fields. Our approach delivers high-quality reconstructions, and reduces the reconstruction error by a factor of 2:5 on average compared to the state-of-the-art, given the same parameter count or storage capacity. Compared to the best-performing alternative, our method produced higher accuracy models on 94% of the 400 input shape and parameter count combinations tested., Comment: Eric Hedlin and Jinfan Yang contributed equally to this work

We propose a generative framework, FaceLit, capable of generating a 3D face that can be rendered at various user-defined lighting conditions and views, learned purely from 2D images in-the-wild without any manual annotation. Unlike existing works that require careful capture setup or human labor, we rely on off-the-shelf pose and illumination estimators. With these estimates, we incorporate the Phong reflectance model in the neural volume rendering framework. Our model learns to generate shape and material properties of a face such that, when rendered according to the natural statistics of pose and illumination, produces photorealistic face images with multiview 3D and illumination consistency. Our method enables photorealistic generation of faces with explicit illumination and view controls on multiple datasets - FFHQ, MetFaces and CelebA-HQ. We show state-of-the-art photorealism among 3D aware GANs on FFHQ dataset achieving an FID score of 3.5., Comment: CVPR 2023

We present a novel method to provide efficient and highly detailed reconstructions. Inspired by wavelets, we learn a neural field that decompose the signal both spatially and frequency-wise. We follow the recent grid-based paradigm for spatial decomposition, but unlike existing work, encourage specific frequencies to be stored in each grid via Fourier features encodings. We then apply a multi-layer perceptron with sine activations, taking these Fourier encoded features in at appropriate layers so that higher-frequency components are accumulated on top of lower-frequency components sequentially, which we sum up to form the final output. We demonstrate that our method outperforms the state of the art regarding model compactness and convergence speed on multiple tasks: 2D image fitting, 3D shape reconstruction, and neural radiance fields. Our code is available at https://github.com/ubc-vision/NFFB.

We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose, Comment: Accepted at BMVC 2022. Supplementary qualitative results - https://aritro30.github.io/results/. Code at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose

Neural fields model signals by mapping coordinate inputs to sampled values. They are becoming an increasingly important backbone architecture across many fields from vision and graphics to biology and astronomy. In this paper, we explore the differences between common conditioning mechanisms within these networks, an essential ingredient in shifting neural fields from memorization of signals to generalization, where the set of signals lying on a manifold is modelled jointly. In particular, we are interested in the scaling behaviour of these mechanisms to increasingly high-dimensional conditioning variables. As we show in our experiments, high-dimensional conditioning is key to modelling complex data distributions, thus it is important to determine what architecture choices best enable this when working on such problems. To this end, we run experiments modelling 2D, 3D, and 4D signals with neural fields, employing concatenation, hyper-network, and attention-based conditioning strategies -- a necessary but laborious effort that has not been performed in the literature. We find that attention-based conditioning outperforms other approaches in a variety of settings.

We propose a new framework for extracting visual information about a scene only using audio signals. Audio-based methods can overcome some of the limitations of vision-based methods i.e., they do not require "line-of-sight", are robust to occlusions and changes in illumination, and can function as a backup in case vision/lidar sensors fail. Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps. First, we train a Vector-Quantized Variational Auto-Encoder to learn the data manifold of the particular visual modality we are interested in. Second, we train an Audio Transformation network to map multi-channel audio signals to the latent representation of the corresponding visual sample. We show that our method is able to produce meaningful images from audio using a publicly available audio/visual dataset. In particular, we consider the prediction of the following visual modalities from audio: depth and semantic segmentation. We hope the findings of our work can facilitate further research in visual information extraction from audio. Code is available at: https://github.com/ubc-vision/audio_manifold.

We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods., Comment: Project website: https://neuralbf.github.io

Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in an image. This greatly limits their applicability, as each instance must be isolated before applying the method-an issue that is never discussed or evaluated. We thus propose a novel method to learn Task-agnostic, UnSupervised Keypoints (TUSK) which can deal with multiple instances. To achieve this, instead of the commonly-used strategy of detecting multiple heatmaps, each dedicated to a specific keypoint type, we use a single heatmap for detection, and enable unsupervised learning of keypoint types through clustering. Specifically, we encode semantics into the keypoints by teaching them to reconstruct images from a sparse set of keypoints and their descriptors, where the descriptors are forced to form distinct clusters in feature space around learned prototypes. This makes our approach amenable to a wider range of tasks than any previous unsupervised keypoint method: we show experiments on multiple-instance detection and classification, object discovery, and landmark detection-all unsupervised-with performance on par with the state of the art, while also being able to deal with multiple instances.

To correct for respiratory motion in PET imaging, an interpretable and unsupervised deep learning technique, FlowNet-PET, was constructed. The network was trained to predict the optical flow between two PET frames from different breathing amplitude ranges. The trained model aligns different retrospectively-gated PET images, providing a final image with similar counting statistics as a non-gated image, but without the blurring effects. FlowNet-PET was applied to anthropomorphic digital phantom data, which provided the possibility to design robust metrics to quantify the corrections. When comparing the predicted optical flows to the ground truths, the median absolute error was found to be smaller than the pixel and slice widths. The improvements were illustrated by comparing against images without motion and computing the intersection over union (IoU) of the tumors as well as the enclosed activity and coefficient of variation (CoV) within the no-motion tumor volume before and after the corrections were applied. The average relative improvements provided by the network were 64%, 89%, and 75% for the IoU, total activity, and CoV, respectively. FlowNet-PET achieved similar results as the conventional retrospective phase binning approach, but only required one sixth of the scan duration. The code and data have been made publicly available (https://github.com/teaghan/FlowNet_PET).

Many human pose estimation methods estimate Skinned Multi-Person Linear (SMPL) models and regress the human joints from these SMPL estimates. In this work, we show that the most widely used SMPL-to-joint linear layer (joint regressor) is inaccurate, which may mislead pose evaluation results. To achieve a more accurate joint regressor, we propose a method to create pseudo-ground-truth SMPL poses, which can then be used to train an improved regressor. Specifically, we optimize SMPL estimates coming from a state-of-the-art method so that its projection matches the silhouettes of humans in the scene, as well as the ground-truth 2D joint locations. While the quality of this pseudo-ground-truth is challenging to assess due to the lack of actual ground-truth SMPL, with the Human 3.6m dataset, we qualitatively show that our joint locations are more accurate and that our regressor leads to improved pose estimations results on the test set without any need for retraining. We release our code and joint regressor at https://github.com/ubc-vision/joint-regressor-refinement

Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences. We propose a novel framework to reconstruct the human and the scene that can be rendered with novel human poses and views from just a single in-the-wild video. Given a video captured by a moving camera, we train two NeRF models: a human NeRF model and a scene NeRF model. To train these models, we rely on existing methods to estimate the rough geometry of the human and the scene. Those rough geometry estimates allow us to create a warping field from the observation space to the canonical pose-independent space, where we train the human model in. Our method is able to learn subject specific details, including cloth wrinkles and accessories, from just a 10 seconds video clip, and to provide high quality renderings of the human under novel poses, from novel views, together with the background.

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification., Comment: 21 pages, CVPR2022

We propose a novel optimization framework that crops a given image based on user description and aesthetics. Unlike existing image cropping methods, where one typically trains a deep network to regress to crop parameters or cropping actions, we propose to directly optimize for the cropping parameters by repurposing pre-trained networks on image captioning and aesthetic tasks, without any fine-tuning, thereby avoiding training a separate network. Specifically, we search for the best crop parameters that minimize a combined loss of the initial objectives of these networks. To make the optimization table, we propose three strategies: (i) multi-scale bilinear sampling, (ii) annealing the scale of the crop region, therefore effectively reducing the parameter space, (iii) aggregation of multiple optimization results. Through various quantitative and qualitative evaluations, we show that our framework can produce crops that are well-aligned to intended user descriptions and aesthetically pleasing.

We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are regressed by the neural network given the scene encoding. This leads to a few-shot learning framework, where attributes are discovered automatically by the framework, when annotations are not provided. We apply our method to various scenes with different types of controllable attributes (e.g. expression control on human faces, or state control in movement of inanimate objects). Overall, we demonstrate, to the best of our knowledge, for the first time novel view and novel attribute re-rendering of scenes from a single video., Comment: Project page: https://conerf.github.io/

We introduce layered controllable video generation, where we, without any supervision, decompose the initial frame of a video into foreground and background layers, with which the user can control the video generation process by simply manipulating the foreground mask. The key challenges are the unsupervised foreground-background separation, which is ambiguous, and ability to anticipate user manipulations with access to only raw video sequences. We address these challenges by proposing a two-stage learning procedure. In the first stage, with the rich set of losses and dynamic foreground size prior, we learn how to separate the frame into foreground and background layers and, conditioned on these layers, how to generate the next frame using VQ-VAE generator. In the second stage, we fine-tune this network to anticipate edits to the mask, by fitting (parameterized) control to the mask from future frame. We demonstrate the effectiveness of this learning and the more granular control mechanism, while illustrating state-of-the-art performance on two benchmark datasets. We provide a video abstract as well as some video results on https://gabriel-huang.github.io/layered_controllable_video_generation, Comment: This paper has been accepted to ECCV 2022 as an Oral paper

We present a method for learning a generative 3D model based on neural radiance fields, trained solely from data with only single views of each object. While generating realistic images is no longer a difficult task, producing the corresponding 3D structure such that they can be rendered from different views is non-trivial. We show that, unlike existing methods, one does not need multi-view data to achieve this goal. Specifically, we show that by reconstructing many images aligned to an approximate canonical pose with a single network conditioned on a shared latent space, you can learn a space of radiance fields that models shape and appearance for a class of objects. We demonstrate this by training models to reconstruct object categories using datasets that contain only one view of each subject without depth or geometry information. Our experiments show that we achieve state-of-the-art results in novel view synthesis and high-quality results for monocular depth prediction., Comment: See https://lolnerf.github.io for additional results

Implicit representations of geometry, such as occupancy fields or signed distance fields (SDF), have recently re-gained popularity in encoding 3D solid shape in a functional form. In this work, we introduce medial fields: a field function derived from the medial axis transform (MAT) that makes available information about the underlying 3D geometry that is immediately useful for a number of downstream tasks. In particular, the medial field encodes the local thickness of a 3D shape, and enables O(1) projection of a query point onto the medial axis. To construct the medial field we require nothing but the SDF of the shape itself, thus allowing its straightforward incorporation in any application that relies on signed distance fields. Working in unison with the O(1) surface projection supported by the SDF, the medial field opens the door for an entirely new set of efficient, shape-aware operations on implicit representations. We present three such applications, including a modification to sphere tracing that renders implicit representations with better convergence properties, a fast construction method for memory-efficient rigid-body collision proxies, and an efficient approximation of ambient occlusion that remains stable with respect to viewpoint variations.

We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other. By doing so, one has the option to query only the points of interest and retrieve sparse correspondences, or to query all points in an image and obtain dense mappings. Importantly, in order to capture both local and global priors, and to let our model relate between image regions using the most relevant among said priors, we realize our network using a transformer. At inference time, we apply our correspondence network by recursively zooming in around the estimates, yielding a multiscale pipeline able to provide highly-accurate correspondences. Our method significantly outperforms the state of the art on both sparse and dense correspondence problems on multiple datasets and tasks, ranging from wide-baseline stereo to optical flow, without any retraining for a specific dataset. We commit to releasing data, code, and all the tools necessary to train from scratch and ensure reproducibility.

The Canada-France Imaging Survey (CFIS) will consist of deep, high-resolution r-band imaging over ~5000 square degrees of the sky, representing a first-rate opportunity to identify recently-merged galaxies. Due to the large number of galaxies in CFIS, we investigate the use of a convolutional neural network (CNN) for automated merger classification. Training samples of post-merger and isolated galaxy images are generated from the IllustrisTNG simulation processed with the observational realism code RealSim. The CNN's overall classification accuracy is 88 percent, remaining stable over a wide range of intrinsic and environmental parameters. We generate a mock galaxy survey from IllustrisTNG in order to explore the expected purity of post-merger samples identified by the CNN. Despite the CNN's good performance in training, the intrinsic rarity of post-mergers leads to a sample that is only ~6 percent pure when the default decision threshold is used. We investigate trade-offs in purity and completeness with a variable decision threshold and find that we recover the statistical distribution of merger-induced star formation rate enhancements. Finally, the performance of the CNN is compared with both traditional automated methods and human classifiers. The CNN is shown to outperform Gini-M20 and asymmetry methods by an order of magnitude in post-merger sample purity on the mock survey data. Although the CNN outperforms the human classifiers on sample completeness, the purity of the post-merger sample identified by humans is frequently higher, indicating that a hybrid approach to classifications may be an effective solution to merger classifications in large surveys., Comment: 21 pages, 19 figures, 2 tables, Accepted for publication in MNRAS

We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of randomly rotated objects. Our key idea is to aggregate the attention masks into semantic keypoints, and use these to supervise a decomposition that satisfies the capsule invariance/equivariance properties. This not only enables the training of a semantically consistent decomposition, but also allows us to learn a canonicalization operation that enables object-centric reasoning. To train our neural network we require neither classification labels nor manually-aligned training datasets. Yet, by learning an object-centric representation in a self-supervised manner, our method outperforms the state-of-the-art on 3D point cloud reconstruction, canonicalization, and unsupervised classification., Comment: NeurIPS 2021; The first two authors contributed equally; Project website: https://canonical-capsules.github.io

With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is very computationally intensive, limiting their applicability in practical scenarios. In this paper, we propose a technique based on spatial decomposition capable of mitigating this issue. Our key observation is that there are diminishing returns in employing larger (deeper and/or wider) networks. Hence, we propose to spatially decompose a scene and dedicate smaller networks for each decomposed part. When working together, these networks can render the whole scene. This allows us near-constant inference time regardless of the number of decomposed parts. Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering. Our experiments show that for real-world scenes, our method provides up to 3x more efficient inference than NeRF (with the same rendering quality), or an improvement of up to 1.0~dB in PSNR (for the same inference cost).