We introduce Uncommon Objects in 3D (uCO3D), a new object-centric dataset for 3D deep learning and 3D generative AI. uCO3D is the largest publicly-available collection of high-resolution videos of objects with 3D annotations that ensures full-360° coverage. uCO3D is significantly more diverse than MVImgNet and CO3Dv2, covering more than 1,000 object categories. It is also of higher quality, due to extensive quality checks of both the collected videos and the 3D annotations. Similar to analogous datasets, uCO3D contains annotations for 3D camera poses, depth maps and sparse point clouds. In addition, each object is equipped with a caption and a 3D Gaussian Splat reconstruction. We train several large 3D models on MVImgNet, CO3Dv2, and uCO3D and obtain superior results using the latter, showing that uCO3D is better for learning applications.

Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somewhat unstable, and prone to artifacts. A mitigation is to fine-tune the 2D generator to be multi-view aware, which can help distillation or can be combined with reconstruction networks to output 3D objects directly. In this paper, we further explore the design space of text-to-3D models. We significantly improve multi-view generation by considering video instead of image generators. Combined with a 3D reconstruction algorithm which, by using Gaussian splatting, can optimize a robust image-based loss, we directly produce high-quality 3D outputs from the generated views. Our new method, IM-3D, reduces the number of evaluations of the 2D generator network 10-100$\times$, resulting in a much more efficient pipeline, better quality, fewer geometric inconsistencies, and higher yield of usable 3D assets.

We present Meta 3D AssetGen (AssetGen), a significant advancement in text-to-3D generation which produces faithful, high-quality meshes with texture and material control. Compared to works that bake shading in the 3D object’s appearance, AssetGen outputs physically-based rendering (PBR) materials, supporting realistic relighting. AssetGen generates first several views of the object with separate shaded and albedo appearance channels, and then reconstructs colours, metalness and roughness in 3D, using a deferred shading loss for efficient supervision. It also uses a sign-distance function to represent 3D shape more reliably and introduces a corresponding loss for direct shape supervision. This is implemented using fused kernels for high memory efficiency. After mesh extraction, a texture refinement transformer operating in UV space significantly improves sharpness and details. AssetGen achieves 17% improvement in Chamfer Distance and 40% in LPIPS over the best concurrent work for few-view reconstruction, and a human preference of 72% over the best industry competitors of comparable speed, including those that support PBR. Project page with generated assets: https://assetgen.github.io

We introduce the novel-view acoustic synthesis (NVAS) task: given the sight and sound observed at a source view-point, can we synthesize the sound of that scene from an unseen target viewpoint? We propose a neural rendering approach: Visually-Guided Acoustic Synthesis (ViGAS) network that learns to synthesize the sound of an arbitrary point in space by analyzing the input audio-visual cues. To benchmark this task, we collect two first-of-their-kind large-scale multi-view audio-visual datasets, one synthetic and one real. We show that our model successfully reasons about the spatial cues and synthesizes faithful audio on both datasets. To our knowledge, this work represents the very first formulation, dataset, and approach to solve the novel-view acoustic synthesis task, which has exciting potential applications ranging from AR/VR to art and design. Unlocked by this work, we believe that the future of novel-view synthesis is in multi-modal learning from videos.

We consider the problem of reconstructing a dynamic scene observed from a stereo camera. Most existing meth-ods for depth from stereo treat different stereo frames in-dependently, leading to temporally inconsistent depth pre-dictions. Temporal consistency is especially important for immersive AR or VR scenarios, where flickering greatly di-minishes the user experience. We propose DynamicStereo, a novel transformer-based architecture to estimate dispar-ity for stereo videos. The network learns to pool information from neighboring frames to improve the temporal consistency of its predictions. Our architecture is designed to process stereo videos efficiently through divided attention layers. We also introduce Dynamic Replica, a new bench-mark dataset containing synthetic videos of people and ani-mals in scanned environments, which provides complemen-tary training and evaluation data for dynamic stereo closer to real applications than existing datasets. Training with this dataset further improves the quality of predictions of our proposed DynamicStereo as well as prior methods. Finally, it acts as a benchmark for consistent stereo methods. Project page: https://dynamic-stereo.github.io/

Obtaining photorealistic reconstructions of objects from sparse views is inherently ambiguous and can only be achieved by learning suitable reconstruction priors. Earlier works on sparse rigid object reconstruction successfully learned such priors from large datasets such as CO3D. In this paper, we extend this approach to dynamic objects. We use cats and dogs as a representative example and introduce Common Pets in 3D (CoP3D), a collection of crowd-sourced videos of approximately 4,200 distinct pets. CoP3D is one of the first large-scale datasets for benchmarking non-rigid 3D reconstruction “in the wild”. We also propose Tracker-NeRF, a method for learning 4D reconstruction from our dataset. At test time, given a small number of video frames of an unseen object, Tracker-NeRF predicts the trajectories of its 3D points and generates new views, interpolating viewpoint and time. Results on CoP3D reveal significantly better non-rigid new-view synthesis performance than existing baselines. The data will be available on the project webpage: https://cop3d.github.io/.

We introduce Replay, a collection of multi-view, multi-modal videos of humans interacting socially. Each scene is filmed in high production quality, from different view-points with several static cameras, as well as wearable action cameras, and recorded with a large array of microphones at different positions in the room. Overall, the dataset contains over 4000 minutes of footage and over 7 million timestamped high-resolution frames annotated with camera poses and partially with foreground masks. The Replay dataset has many potential applications, such as novel-view synthesis, 3D reconstruction, novel-view acoustic synthesis, human body and face analysis, and training generative models. We provide a benchmark for training and evaluating novel-view synthesis, with two scenarios of different difficulty. Finally, we evaluate several baseline state-of-the-art methods on the new benchmark.

Video provides us with the spatio-temporal consistency needed for visual learning. Recent approaches have utilized this signal to learn correspondence estimation from closeby frame pairs. However, by only relying on close-by frame pairs, those approaches miss out on the richer long-range consistency between distant overlapping frames. To address this, we propose a self-supervised approach for correspondence estimation that learns from multiview consistency in short RGB-D video sequences. Our approach combines pairwise correspondence estimation and registration with a novel SE(3) transformation synchronization algorithm. Our key insight is that self-supervised multiview registration allows us to obtain correspondences over longer time frames; increasing both the diversity and difficulty of sampled pairs. We evaluate our approach on indoor scenes for correspondence estimation and RGB-D pointcloud registration and find that we perform on-par with supervised approaches.

We consider the problem of reconstructing the depth of dynamic objects from videos. Recent progress in dynamic video depth prediction has focused on improving the output of monocular depth estimators by means of multi-view constraints while imposing little to no restrictions on the deformation of the dynamic parts of the scene. However, the theory of Non-Rigid Structure from Motion prescribes to constrain the deformations for 3D reconstruction. We thus propose a new model that departs significantly from this prior work. The idea is to fit a dynamic point cloud to the video data using Sinkhorn's algorithm to associate the 3D points to 2D pixels and use a differentiable point renderer to ensure the compatibility of the 3D deformations with the measured optical flow. In this manner, our algorithm, called Keypoint Transporter, models the overall deformation of the object within the entire video, so it can constrain the reconstruction correspondingly. Compared to weaker deformation models, this significantly reduces the reconstruction ambiguity and, for dynamic objects, allows Keypoint Transporter to obtain reconstructions of the quality superior or at least comparable to prior approaches while being much faster and reliant on a pre-trained monocular depth estimator network. To assess the method, we evaluate on new datasets of synthetic videos depicting dynamic humans and animals with ground-truth depth. We also show qualitative results on crowd-sourced real-world videos of pets.

Prior work for articulated 3D shape reconstruction often relies on specialized multi-view and depth sensors or pre-built deformable 3D models. Such methods do not scale to diverse sets of objects in the wild. We present a method that requires neither of them. It aims to create high-fidelity, articulated 3D models from many casual RGB videos in a differentiable rendering framework. Our key in-sight is to merge three schools of thought: (1) classic deformable shape models that make use of articulated bones and blend skinning, (2) canonical embeddings that establish correspondences between pixels and a canonical 3D model, and (3) volumetric neural radiance fields (NeRFs) that are amenable to gradient-based optimization. We introduce neural blend skinning models that allow for differentiable and invertible articulated deformations. When combined with canonical embeddings, such models allow us to establish dense correspondences across videos that can be self-supervised with cycle consistency. On real and synthetic datasets, our method shows higher-fidelity 3D reconstructions than prior works for humans and animals, with the ability to render realistic images from novel viewpoints. Project page: https://banmo-www.github.io/.

Differently from 2D image datasets such as COCO, largescale human datasets with 3D ground-truth annotations are very difficult to obtain in the wild. In this paper, we address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. Remarkably, the resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in the-wild benchmarks such as 3DPW. Additionally, training on our augmented data is straightforward as it does not require to mix multiple and incompatible 2D and 3D datasets or to use complicated network architectures and training procedures. This simplified pipeline affords additional improvements, including injecting extreme crop augmentations to better reconstruct highly truncated people, and incorporating auxiliary inputs to improve 3D pose estimation accuracy. It also reduces the dependency on 3D datasets such as H36M that have restrictive licenses. We also use our method to introduce new benchmarks for the study of real-world challenges such as occlusions, truncations, and rare body poses. In order to obtain such high quality 3D pseudo-annotations, inspired by progress in internal learning, we introduce Exemplar Fine-Tuning (EFT). EFT combines the re-projection accuracy of fitting methods like SMPLify with a 3D pose prior implicitly captured by a pre-trained 3D pose regressor network. We show that EFT produces 3D annotations that result in better downstream performance and are qualitatively preferable in an extensive human-based assessment.

We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i.e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them. The interpolation, expressed as a deformation field, changes the pose of the source shape to resemble the target, but leaves the object identity unchanged. NeuroMorph uses an elegant architecture combining graph convolutions with global feature pooling to extract local features. During training, the model is incentivized to create realistic deformations by approximating geodesics on the underlying shape space manifold. This strong geometric prior allows to train our model end-to-end and in a fully unsupervised manner without requiring any manual correspondence annotations. NeuroMorph works well for a large variety of input shapes, including non-isometric pairs from different object categories. It obtains state-of-the-art results for both shape correspondence and interpolation tasks, matching or surpassing the performance of recent unsupervised and supervised methods on multiple benchmarks.

We tackle the problem of learning the geometry of multiple categories of deformable objects jointly. Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects. However, training such models requires to initialize inter-category correspondences by hand. This is suboptimal and the resulting models fail to maintain correct correspondences as individual categories are learned. In this paper, we show that improved correspondences can be learned automatically as a natural byproduct of learning category-specific dense pose predictors. To do this, we express correspondences between different categories and between images and categories using a unified embedding. Then, we use the latter to enforce two constraints: symmetric inter-category cycle consistency and a new asymmetric image-to-category cycle consistency. Without any manual annotations for the intercategory correspondences, we obtain state-of-the-art alignment results, outperforming dedicated methods for matching 3D shapes. Moreover, the new model is also better at the task of dense pose prediction than prior work.

Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a “transposed” version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images.Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.We will opensource our code and trained models to reproduce the reported results.

Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each case makes this strategy impractical, despite important applications in natural conservation, science and business. We show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by (1) establishing a DensePose model for the new animal which is also geometrically aligned to humans (2) introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, (3) finding which combination of known classes can be transferred most effectively to the new animal and (4) using self-calibrated uncertainty heads to generate pseudo-labels graded by quality for training a model for this class. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach, showing excellent transfer learning performance.

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e., humans), often with significant manual work involved. However, scaling the geometry understanding to all objects in nature requires more automated approaches that can also express correspondences between related, but geometrically different objects. To this end, we propose a new, learnable image-based representation of dense correspondences. Our model predicts, for each pixel in a 2D image, an embedding vector of the corresponding vertex in the object mesh, therefore establishing dense correspondences between image pixels and 3D object geometry. We demonstrate that the proposed approach performs on par or better than the state-of-the-art methods for dense pose estimation for humans, while being conceptually simpler. We also collect a new in-the-wild dataset of dense correspondences for animal classes and demonstrate that our framework scales naturally to the new deformable object categories.

DensePose supersedes traditional landmark detectors by densely mapping image pixels to body surface coordinates. This power, however, comes at a greatly increased annotation cost, as supervising the model requires to manually label hundreds of points per pose instance. In this work, we thus seek methods to significantly slim down the DensePose annotations, proposing more efficient data collection strategies. In particular, we demonstrate that if annotations are collected in video frames, their efficacy can be multiplied for free by using motion cues. To explore this idea, we introduce DensePose-Track, a dataset of videos where selected frames are annotated in the traditional DensePose manner. Then, building on geometric properties of the DensePose mapping, we use the video dynamic to propagate ground-truth annotations in time as well as to learn from Siamese equivariance constraints. Having performed exhaustive empirical evaluation of various data annotation and learning strategies, we demonstrate that doing so can deliver significantly improved pose estimation results over strong baselines. However, despite what is suggested by some recent works, we show that merely synthesizing motion patterns by applying geometric transformations to isolated frames is significantly less effective, and that motion cues help much more when they are extracted from videos.

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, there exists a certain canonicalization function of the reconstructed shapes. Then, we learn the canonicalization function together with the reconstruction one, which constrains the result to be consistent. We demonstrate state-of-the-art reconstruction results for methods that do not use ground-truth 3D supervision for a number of benchmarks, including Up3D and PASCAL3D+.

Many machine learning methods depend on human supervision to achieve optimal performance. However, in tasks such as DensePose, where the goal is to establish dense visual correspondences between images, the quality of manual annotations is intrinsically limited. We address this issue by augmenting neural network predictors with the ability to output a distribution over labels, thus explicitly and introspectively capturing the aleatoric uncertainty in the annotations. Compared to previous works, we show that correlated error fields arise naturally in applications such as DensePose and these fields can be modeled by deep networks, leading to a better understanding of the annotation errors. We show that these models, by understanding uncertainty better, can solve the original DensePose task more accurately, thus setting the new state-of-the-art accuracy in this benchmark. Finally, we demonstrate the utility of the uncertainty estimates in fusing the predictions of produced by multiple models, resulting in a better and more principled approach to model ensembling which can further improve accuracy.

In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an inpainting network that can fill in missing ground truth values and report improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter. We further improve accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Supplementary materials, data, code, and videos are provided on the project page http://densepose.org.

Model selection methods based on stochastic regularization have been widely used in deep learning due to their simplicity and effectiveness. The well-known Dropout method treats all units, visible or hidden, in the same way, thus ignoring any a priori information related to grouping or structure. Such structure is present in multi-modal learning applications such as affect analysis and gesture recognition, where subsets of units may correspond to individual modalities. Here we describe Modout, a model selection method based on stochastic regularization, which is particularly useful in the multi-modal setting. Different from other forms of stochastic regularization, it is capable of learning whether or when to fuse two modalities in a layer, which is usually considered to be an architectural hyper-parameter by deep learning researchers and practitioners. Modout is evaluated on two real multi-modal datasets. The results indicate improved performance compared to other forms of stochastic regularization. The result on the Montalbano dataset shows that learning a fusion structure by Modout is on par with a state-of-the-art carefully designed architecture.

The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future. We develop an autoregressive convolutional neural network that learns to iteratively generate multiple frames. Our results on the Cityscapes dataset show that directly predicting future segmentations is substantially better than predicting and then segmenting future RGB frames. Prediction results up to half a second in the future are visually convincing and are much more accurate than those of a baseline based on warping semantic segmentations using optical flow.

Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In all cases, the attacks based on Houdini achieve higher success rate than those based on the traditional surrogates used to train the models while using a less perceptible adversarial perturbation.

We present a method for gesture detection and localisation based on multi-scale and multi-modal deep learning. Each visual modality captures spatial information at a particular spatial scale (such as motion of the upper body or a hand), and the whole system operates at three temporal scales. Key to our technique is a training strategy which exploits: i) careful initialization of individual modalities; and ii) gradual fusion involving random dropping of separate channels (dubbed ModDrop) for learning cross-modality correlations while preserving uniqueness of each modality-specific representation. We present experiments on the ChaLearn 2014 Looking at People Challenge gesture recognition track, in which we placed first out of 17 teams. Fusing multiple modalities at several spatial and temporal scales leads to a significant increase in recognition rates, allowing the model to compensate for errors of the individual classifiers as well as noise in the separate channels. Furthermore, the proposed ModDrop training technique ensures robustness of the classifier to missing signals in one or several channels to produce meaningful predictions from any number of available modalities. In addition, we demonstrate the applicability of the proposed fusion scheme to modalities of arbitrary nature by experiments on the same dataset augmented with audio.

This paper presents a method for extracting blur/sharp regions of interest (ROI) that benefits of using a combination of edge and region based approaches. It can be considered as a preliminary step for many vision applications tending to focus only on the most salient areas in low depth-of-field images. To localize focused regions, we first classify each edge as either sharp or blurred based on gradient profile width estimation. Then a mean shift oversegmentation allows to label each region using the density of marked edge pixels inside. Finally, the proposed algorithm is tested on a dataset of high resolution images and the results are compared with the manually established ground truth. It is shown that the given method outperforms known state-of-the-art techniques in terms of F-measure. The robustness of the method is confirmed by means of additional experiments on images with different values of defocus degree.