CVPR 2022 Papers

Automated generation of 3D human motions from text is a challenging problem. The generated motions are expected to be sufficiently diverse to explore the text-grounded motion space, and more importantly, accurately depicting the content in prescribed text descriptions. Here we tackle this problem with a two-stage approach: text2length sampling and text2motion generation. Text2length involves sampling from the learned distribution function of motion lengths conditioned on the input text. This is followed by our text2motion module using temporal variational autoencoder to synthesize a diverse set of human motions of the sampled lengths. Instead of directly engaging with pose sequences, we propose motion snippet code as our internal motion representation, which captures local semantic motion contexts and is empirically shown to facilitate the generation of plausible motions faithful to the input text. Moreover, a large-scale dataset of scripted 3D Human motions, HumanML3D, is constructed, consisting of 14,616 motion clips and 44,970 text descriptions. Extensive empirical experiments demonstrate the effectiveness of our approach. Project webpage: https://ericguo5513.github.io/text-to-motion/.

Occlusions are a common occurrence in unconstrained face images. Single image 3D reconstruction from such face images often suffers from corruption due to the presence of occlusions. Furthermore, while a plurality of 3D reconstructions is plausible in the occluded regions, existing approaches are limited to generating only a single solution. To address both of these challenges, we present Diverse3DFace, which is specifically designed to simultaneously generate a diverse and realistic set of 3D reconstructions from a single occluded face image. It consists of three components: a global+local shape fitting process, a graph neural network-based mesh VAE, and a Determinantal Point Process based diversity promoting iterative optimization procedure. Quantitative and qualitative comparisons of 3D reconstruction on occluded faces show that Diverse3DFace can estimate 3D shapes that are consistent with the visible regions in the target image while exhibiting high, yet realistic, levels of diversity on the occluded regions. On face images occluded by masks, glasses, and other random objects, Diverse3DFace generates a distribution of 3D shapes having 50% higher diversity on the occluded regions compared to the baselines. Moreover, our closest sample to the ground truth has 40% lower MSE than the singular reconstructions by existing approaches. Code and data available at: https://github.com/human-analysis/diverse3dface

We introduce AiD Regen, a novel system that generates 3D wound models combining 2D semantic segmentation with 3D reconstruction so that they can be printed via 3D bio-printers during the surgery to treat diabetic foot ulcers (DFUs). AiD Regen seamlessly binds the full pipeline, which includes RGB-D image capturing, semantic segmentation, boundary-guided point-cloud processing, 3D model reconstruction, and 3D printable G-code generation, into a single system that can be used out of the box. We developed a multi-stage data preprocessing method to handle small and unbalanced DFU image datasets. AiD Regen's human-in-the-loop machine learning interface enables clinicians to not only create 3D regenerative patches with just a few touch interactions but also customize and confirm wound boundaries. As evidenced by our experiments, our model outperforms prior wound segmentation models and our reconstruction algorithm is capable of generating 3D wound models with compelling accuracy. We further conducted a case study on a real DFU patient and demonstrated the effectiveness of AiD Regen in treating DFU wounds.

As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation of the target outputs given the visual inputs. Although the estimation accuracy of the proposed automatic methods continues to improve, interactive refinement is oftentimes necessary for further correction. Recently, feature backpropagating refinement scheme (f-BRS) has been proposed for the task of interactive segmentation, which enables efficient optimization of a small set of auxiliary variables inserted into the pretrained network to produce object segmentation that better aligns with user inputs. However, the proposed auxiliary variables only contain channel-wise scale and bias, limiting the optimization to global refinement only. In this work, in order to generalize backpropagating refinement for a wide range of dense prediction tasks, we introduce a set of G-BRS (Generalized Backpropagating Refinement Scheme) layers that enable both global and localized refinement for the following tasks: interactive segmentation, semantic segmentation, image matting and monocular depth estimation. Experiments on SBD, Cityscapes, Mapillary Vista, Composition-1k and NYU-Depth-V2 show that our method can successfully generalize and significantly improve performance of existing pretrained state-of-the-art models with only a few clicks.

Recent advances of deep learning-based approaches have achieved remarkable performance on appearance-based gaze estimation. However, due to the shortage of target domain data and absence of target labels, generalizing gaze estimation algorithm to unseen environments is still challenging. In this paper, we discover the rotation-consistency property in gaze estimation and introduce the 'sub-label' for unsupervised domain adaptation. Consequently, we propose the Rotation-enhanced Unsupervised Domain Adaptation (RUDA) for gaze estimation. First, we rotate the original images with different angles for training. Then we conduct domain adaptation under the constraint of rotation consistency. The target domain images are assigned with sub-labels, derived from relative rotation angles rather than untouchable real labels. With such sub-labels, we propose a novel distribution loss that facilitates the domain adaptation. We evaluate the RUDA framework on four cross-domain gaze estimation tasks. Experimental results demonstrate that it improves the performance over the baselines with gains ranging from 12.2% to 30.5%. Our framework has the potential to be used in other computer vision tasks with physical constraints.

Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of simultaneously segmenting the novel categories with very few examples and the base categories with sufficient examples. It is the first study showing that previous representative state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image. Both two contributions are experimentally shown to have substantial practical merit. Extensive experiments on Pascal-VOC and COCO manifest the effectiveness of CAPL, and CAPL generalizes well to FS-Seg by achieving competitive performance. Code will be made publicly available.

In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. Existing recognition methods are not able to deal with this setting, because they make several restrictive assumptions, such as the unlabelled instances only coming from known -- or unknown -- classes, and the number of unknown classes being known a-priori. We address the more unconstrained setting, naming it 'Generalized Category Discovery', and challenge all these assumptions. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. Next, we propose the use of vision transformers with contrastive representation learning for this open-world setting. We then introduce a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines. Finally, we also propose a new approach to estimate the number of classes in the unlabelled data. We thoroughly evaluate our approach on public datasets for generic object classification and on fine-grained datasets, leveraging the recent Semantic Shift Benchmark suite. Code: https://www.robots.ox.ac.uk/~vgg/research/gcd

Multi-view Stereo (MVS) with known camera parameters is essentially a 1D search problem within a valid depth range. Recent deep learning-based MVS methods typically densely sample depth hypotheses in the depth range, and then construct prohibitively memory-consuming 3D cost volumes for depth prediction. Although coarse-to-fine sampling strategies alleviate this overhead issue to a certain extent, the efficiency of MVS is still an open challenge. In this work, we propose a novel method for highly efficient MVS that remarkably decreases the memory footprint, meanwhile clearly advancing state-of-the-art depth prediction performance. We investigate what a search strategy can be reasonably optimal for MVS taking into account of both efficiency and effectiveness. We first formulate MVS as a binary search problem, and accordingly propose a generalized binary search network for MVS. Specifically, in each step, the depth range is split into 2 bins with extra 1 error tolerance bin on both sides. A classification is performed to identify which bin contains the true depth. We also design three mechanisms to respectively handle classification errors, deal with out-of-range samples and decrease the training memory. The new formulation makes our method only sample a very small number of depth hypotheses in each step, which is highly memory efficient, and also greatly facilitates quick training convergence. Experiments on competitive benchmarks show that our method achieves state-of-the-art accuracy with much less memory. Particularly, our method obtains an overall score of 0.289 on DTU dataset and tops the first place on challenging Tanks and Temples advanced dataset among all the learning-based methods. Our code will be released at https://github.com/MiZhenxing/GBi-Net.

We address the problem of generalizability for multi-view 3D human pose estimation. The standard approach is to first detect 2D keypoints in images and then apply triangulation from multiple views. Even though the existing methods achieve remarkably accurate 3D pose estimation on public benchmarks, most of them are limited to a single spatial camera arrangement and their number. Several methods address this limitation but demonstrate significantly degraded performance on novel views. We propose a stochastic framework for human pose triangulation and demonstrate a superior generalization across different camera arrangements on two public datasets. In addition, we apply the same approach to the fundamental matrix estimation problem, showing that the proposed method can successfully apply to other computer vision problems. The stochastic framework achieves more than 8.8% improvement on the 3D pose estimation task, compared to the state-of-the-art, and more than 30% improvement for fundamental matrix estimation, compared to a standard algorithm.

For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain? This setting, namely generalizable cross-modality segmentation, owning its clinical potential, is much more challenging than other related settings, e.g., domain adaptation. To achieve this goal, we in this paper propose a novel dual-normalization model by leveraging the augmented source-similar and source-dissimilar images during our generalizable segmentation. To be specific, given a single source domain, aiming to simulate the possible appearance change in unseen target domains, we first utilize a nonlinear transformation to augment source-similar and source-dissimilar images. Then, to sufficiently exploit these two types of augmentations, our proposed dual-normalization based model employs a shared backbone yet independent batch normalization layer for separate normalization. Afterward, we put forward a style-based selection scheme to automatically choose the appropriate path in the test stage. Extensive experiments on three publicly available datasets, i.e., BraTS, Cross-Modality Cardiac, and Abdominal Multi-Organ datasets, have demonstrated that our method outperforms other state-of-the-art domain generalization methods. Code is available at https://github.com/zzzqzhou/Dual-Normalization.

Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet under-explored incremental learning problem in which both the class distribution and class-specific domain distribution change over time. In addition to the typical challenges in class incremental learning, this setting also faces the intra-class stability-plasticity dilemma and intra-class domain imbalance problems. To address above issues, we develop a novel domain-aware continual learning method based on the EM framework. Specifically, we introduce a flexible class representation based on the von Mises-Fisher mixture model to capture the intra-class structure, using an expansion-and-reduction strategy to dynamically increase the number of components according to the class complexity. Moreover, we design a bi-level balanced memory to cope with data imbalances within and across classes, which combines with a distillation loss to achieve better inter- and intra-class stability-plasticity trade-off. We conduct exhaustive experiments on three benchmarks: iDigits, iDomainNet and iCIFAR-20. The results show that our approach consistently outperforms previous methods by a significant margin, demonstrating its superiority.

How to learn a universal facial representation that boosts all face analysis tasks This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general facial representation learning. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation by adding a masked image modeling. We perform pre-training on LAION-FACE, a dataset containing a large amount of face image-text pairs, and evaluate the representation capability on multiple downstream tasks. We show that FaRL achieves better transfer performance compared with previous pre-trained models. We also verify its superiority in the low-data regime. More importantly, our model surpasses the state-of-the-art methods on face analysis tasks including face parsing and face alignment.

In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component.We instantiate our general differentiable renderer, which generalizes existing differentiable renderers like SoftRas and DIB-R, with an array of different smoothing distributions to cover a large spectrum of reasonable settings. We evaluate an array of differentiable renderer instantiations on the popular ShapeNet 3D reconstruction benchmark and analyze the implications of our results. Surprisingly, the simple uniform distribution yields the best overall results when averaged over 13 classes; in general, however, the optimal choice of distribution heavily depends on the task.

Appearance-based gaze estimation aims to predict the 3D eye gaze direction from a single image. While recent deep learning-based approaches have demonstrated excellent performance, they usually assume one calibrated face in each input image and cannot output multi-person gaze in real time. However, simultaneous gaze estimation for multiple people in the wild is necessary for real-world applications. In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image. In addition, we design a sophisticated data generation pipeline and propose a new dataset, MPSGaze, which contains full images of multiple people with 3D gaze ground truth. Experimental results demonstrate that our unified framework not only offers a faster speed, but also provides a lower gaze estimation error compared with state-of-the-art methods. This technique can be useful in real-time applications with multiple users.

Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the cost of degraded accuracy in posterior approximation, often underperforming the instance-wise variational optimization. Although the latest semi-amortized approaches mitigate the issue by performing a few variational optimization updates starting from the VAE's amortized inference output, they inherently suffer from computational overhead for inference at test time. In this paper, we address the problem in a completely different way by considering a random inference model, where we model the mean and variance functions of the variational posterior as random Gaussian processes (GP). The motivation is that the deviation of the VAE's amortized posterior distribution from the true posterior can be regarded as random noise, which allows us to view the approximation error as uncertainty in posterior approximation that can be dealt with in a principled GP manner. In particular, our model can quantify the difficulty in posterior approximation by a Gaussian variational density. Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.

Gated cameras hold promise as an alternative to scanning LiDAR sensors with high-resolution 3D depth that is robust to back-scatter in fog, snow, and rain. Instead of sequentially scanning a scene and directly recording depth via the photon time-of-flight, as in pulsed LiDAR sensors, gated imagers encode depth in the relative intensity of a handful of gated slices, captured at megapixel resolution. Although existing methods have shown that it is possible to decode high-resolution depth from such measurements, these methods require synchronized and calibrated LiDAR to supervise the gated depth decoder - prohibiting fast adoption across geographies, training on large unpaired datasets, and exploring alternative applications outside of automotive use cases. In this work, we fill this gap and propose an entirely self-supervised depth estimation method that uses gated intensity profiles and temporal consistency as a training signal. The proposed model is trained end-to-end from gated video sequences, does not require LiDAR or RGB data, and learns to estimate absolute depth values. We take gated slices as input and disentangle the estimation of the scene albedo, depth, and ambient light, which are then used to learn to reconstruct the input slices through a cyclic loss. We rely on temporal consistency between a given frame and neighboring gated slices to estimate depth in regions with shadows and reflections. We experimentally validate that the proposed approach outperforms existing supervised and self-supervised depth estimation methods based on monocular RGB and stereo images, as well as supervised methods based on gated images.

Online action detection is the task of predicting the action as soon as it happens in a streaming video. A major challenge is that the model does not have access to the future and has to solely rely on the history, i.e., the frames observed so far, to make predictions. It is therefore important to accentuate parts of the history that are more informative to the prediction of the current frame. We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction. GateHUB further proposes Future-augmented History (FaH) to make history features more informative by using subsequently observed frames when available. In a single unified framework, GateHUB integrates the transformer's ability of long-range temporal modeling and the recurrent model's capacity to selectively encode relevant information. GateHUB also introduces a background suppression objective to further mitigate false positive background frames that closely resemble the action frames. Extensive validation on three benchmark datasets, THUMOS, TVSeries, and HDD, demonstrates that GateHUB significantly outperforms all existing methods and is also more efficient than the existing best work. Furthermore, a flow-free version of GateHUB is able to achieve higher or close accuracy at 2.8x higher frame rate compared to all existing methods that require both RGB and optical flow information for prediction.

Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for discriminative tasks such as part segmentation, especially when training data is limited. But how do these improvements stack-up against recent advances in self-supervised learning? Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks. Our experiments reveal that not only do the GAN-based approach offer no significant performance advantage, their multi-step training is complex, nearly an order-of-magnitude slower, and can introduce additional bias. These experiments suggest that the inductive biases of generative models, such as their ability to disentangle shape and texture, are well captured by standard feed-forward networks trained using contrastive learning.

Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. However, humans live and walk in the unconstrained 3D space, so projecting the 3D human body onto the 2D plane will discard a lot of crucial information like the viewpoint, shape, and dynamics for gait recognition. Therefore, this paper aims to explore dense 3D representations for gait recognition in the wild, which is a practical yet neglected problem. In particular, we propose a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait. Our framework has two elaborately-designed branches of which one extracts appearance features from silhouettes, the other learns knowledge of 3D viewpoints and shapes from the 3D SMPL model. In addition, due to the lack of suitable datasets, we build the first large-scale 3D representation-based gait recognition dataset, named Gait3D. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene. More importantly, it provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics. Based on Gait3D, we comprehensively compare our method with existing gait recognition approaches, which reflects the superior performance of our framework and the potential of 3D representations for gait recognition in the wild. The code and dataset are available at: https://gait3d.github.io.