CVPR 2022 Papers

Image-based virtual try-on aims to fit an in-shop garment into a clothed person image. To achieve this, a key step is garment warping which spatially aligns the target garment with the corresponding body parts in the person image. Prior methods typically adopt a local appearance flow estimation model. They are thus intrinsically susceptible to difficult body poses/occlusions and large mis-alignments between person and garment images. To overcome this limitation, a novel global appearance flow estimation model is proposed in this work. For the first time, a StyleGAN based architecture is adopted for appearance flow estimation. This enables us to take advantage of a global style vector to encode a whole-image context to cope with the aforementioned challenges. To guide the StyleGAN flow generator to pay more attention to local garment deformation, a flow refinement module is introduced to add local context. Experiment results on a popular virtual try-on benchmark show that our method achieves new state-of-the-art performance. It is particularly effective in a 'in-the-wild' application scenario where the reference image is full-body resulting in a large mis-alignment with the garment image.

Existing GAN inversion methods fail to provide codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleGAN which is not only with less distortions, but also of high quality and flexibility for editing. The proposed model employs a CNN encoder to provide multi-scale image features as keys and values. Meanwhile it regards the style code to be determined for different layers of the generator as queries. It first initializes query tokens as learnable parameters and maps them into W+ space. Then the multi-stage alternate self- and cross-attention are utilized, updating queries with the purpose of inverting the input by the generator. Moreover, based on the inverted code, we investigate the reference- and label-based attribute editing through a pretrained latent classifier, and achieve flexible image-to-image translation with high quality results. Extensive experiments are carried out, showing better performances on both inversion and editing tasks within StyleGAN.

This paper studies domain generalization via domain-invariant representation learning. Existing methods in this direction suppose that a domain can be characterized by styles of its images, and train a network using style-augmented data so that the network is not biased to particular style distributions. However, these methods are restricted to a finite set of styles since they obtain styles for augmentation from a fixed set of external images or by interpolating those of training data. To address this limitation and maximize the benefit of style augmentation, we propose a new method that synthesizes novel styles constantly during training. Our method manages multiple queues to store styles that have been observed so far, and synthesizes novel styles whose distribution is distinct from the distribution of styles in the queues. The style synthesis process is formulated as a monotone submodular optimization, thus can be conducted efficiently by a greedy algorithm. Extensive experiments on four public benchmarks demonstrate that the proposed method is capable of achieving state-of-the-art domain generalization performance.

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convolutional neural networks (CNNs), extracting and maintaining the global information of input images is difficult. Therefore, traditional neural style transfer methods face biased content representation. To address this critical issue, we take long-range dependencies of input images into account for image style transfer by proposing a transformer-based approach called StyTr^2. In contrast with visual transformers for other vision tasks, StyTr^2 contains two different transformer encoders to generate domain-specific sequences for content and style, respectively. Following the encoders, a multi-layer transformer decoder is adopted to stylize the content sequence according to the style sequence. We also analyze the deficiency of existing positional encoding methods and propose the content-aware positional encoding (CAPE), which is scale-invariant and more suitable for image style transfer tasks. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed StyTr^2 compared with state-of-the-art CNN-based and flow-based approaches. Code and models are available at https://github.com/diyiiyiii/StyTR-2.

Scene graph generation (SGG) is to detect object pairs with their relations in an image. Existing SGG approaches often use multi-stage pipelines to decompose this task into object detection, relation graph construction, and dense or dense-to-sparse relation prediction. Instead, from a perspective on SGG as a direct set prediction, this paper presents a simple, sparse, and unified framework, termed as Structured Sparse R-CNN. The key to our method is a set of learnable triplet queries and a structured triplet detector which could be jointly optimized from the training set in an end-to-end manner. Specifically, the triplet queries encode the general prior for object pairs with their relations, and provide an initial guess of scene graphs for subsequent refinement. The triplet detector presents a cascaded architecture to progressively refine the detected scene graphs with the customized dynamic heads. In addition, to relieve the training difficulty of our method, we propose a relaxed and enhanced training strategy based on knowledge distillation from a Siamese Sparse R-CNN. We perform experiments on several datasets: Visual Genome and Open Images V4/V6, and the results demonstrate that our method achieves the state-of-the-art performance. In addition, we also perform in-depth ablation studies to provide insights on our structured modeling in triplet detector design and training strategies. The code and models are made available at https://github.com/MCG-NJU/Structured-Sparse-RCNN.

It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion modeling. To address this problem, we introduce a novel representation on the basis of recent neural scene rendering techniques. The core of our representation is a set of structured local radiance fields, which are anchored to the pre-defined nodes sampled on a statistical human body template. These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field. To learn our representation from RGB data and facilitate pose generalization, we propose to learn the node translations and the detail variations in a conditional generative latent space. Overall, our method enables automatic construction of animatable human avatars for various types of clothes without the need for scanning subject-specific templates, and can generate realistic images with dynamic details for novel poses. Experiment show that our method outperforms state-of-the-art methods both qualitatively and quantitatively.

Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper, we propose a novel structure-aware motion modeling approach, the deformable anchor model (DAM), which can automatically discover the motion structure of arbitrary objects without leveraging their prior structure information. Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information. Moreover, DAM can be further extended to a hierarchical version through the introduction of additional latent anchors to model more complicated structures. By regularizing motion anchors with latent anchor(s), DAM enforces the correspondences between them to ensure the structural information is well captured and preserved. Moreover, DAM can be learned effectively in an unsupervised manner. We validate our proposed DAM for motion transfer on different benchmark datasets. Extensive experiments clearly demonstrate that DAM achieves superior performance relative to existing state-of-the-art methods.

Body reshaping is an important procedure in portrait photo retouching. Due to the complicated structure and multifarious appearance of human bodies, existing methods either fall back on the 3D domain via body morphable model or resort to keypoint-based image deformation, leading to inefficiency and unsatisfied visual quality. In this paper, we address these limitations by formulating an end-to-end flow generation architecture under the guidance of body structural priors, including skeletons and Part Affinity Fields, and achieve unprecedentedly controllable performance under arbitrary poses and garments. A compositional attention mechanism is introduced for capturing both visual perceptual correlations and structural associations of the human body to reinforce the manipulation consistency among related parts. For a comprehensive evaluation, we construct the first large-scale body reshaping dataset, namely BR-5K, which contains 5,000 portrait photos as well as professionally retouched targets. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods in terms of visual performance, controllability, and efficiency. The dataset is available at our website: https://github.com/JianqiangRen/FlowBasedBodyReshaping.

Existing knowledge distillation works for semantic segmentation mainly focus on transfering high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by high-level deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for Semantic Segmentation. Specifically, for structural texture knowledge, we introduce a Contourlet Decomposition Module (CDM) that decomposes low-level features with iterative laplacian pyramid and directional filter bank to mine the structural texture knowledge. For statistical knowledge, we propose a Denoised Texture Intensity Equalization Module (DTIEM) to adaptively extract and enhance statistical texture knowledge through heuristics iterative quantization and denoised operation. Finally, each knowledge learning is supervised by an individual loss function, forcing the student network to mimic the teacher better from a broader perspective. Experiments show that the proposed method achieves state-of-the-art performance on Cityscapes, Pascal VOC 2012 and ADE20K datasets.

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance. Specifically, we first put forward a novel key sampling strategy. For each query point, we sample nearby points densely and distant points sparsely as its keys in a stratified way, which enables the model to enlarge the effective receptive field and enjoy long-range contexts at a low computational cost. Also, to combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance. Besides, we adopt contextual relative position encoding to adaptively capture position information. Finally, a memory-efficient implementation is introduced to overcome the issue of varying point numbers in each window. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets. Code is available at https://github.com/dvlab-research/Stratified-Transformer.

The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or internal weights of the target model. Based on the hypothesis that if an example remains adversarial for multiple models, then it is more likely to transfer the attack capability to other models, the ensemble-based adversarial attack methods are efficient and widely used for black-box attacks. However, ways of ensemble attack are rather less investigated, and existing ensemble attacks simply fuse the outputs of all the models evenly. In this work, we treat the iterative ensemble attack as a stochastic gradient descent optimization process, in which the variance of the gradients on different models may lead to poor local optima. To this end, we propose a novel attack method called the stochastic variance reduced ensemble (SVRE) attack, which could reduce the gradient variance of the ensemble models and take full advantage of the ensemble attack. Empirical results on the standard ImageNet dataset demonstrate that the proposed method could boost the adversarial transferability and outperforms existing ensemble attacks significantly. Code is available at https://github.com/JHL-HUST/SVRE.

Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states. Unlike existing stochastic trajectory prediction methods which usually use a latent variable to represent multi-modality, we explicitly simulate the process of human motion variation from indeterminate to determinate. In this paper, we present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID), in which we progressively discard indeterminacy from all the walkable areas until reaching the desired trajectory. This process is learned with a parameterized Markov chain conditioned by the observed trajectories. We can adjust the length of the chain to control the degree of indeterminacy and balance the diversity and determinacy of the predictions. Specifically, we encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Extensive experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method. Code is available at https://github.com/gutianpei/MID.

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.

We study the effect of adversarial perturbations of images on deep stereo matching networks for the disparity estimation task. We present a method to craft a single set of perturbations that, when added to any stereo image pair in a dataset, can fool a stereo network to significantly alter the perceived scene geometry. Our perturbation images are "universal" in that they not only corrupt estimates of the network on the dataset they are optimized for, but also generalize to different architectures trained on different datasets. We evaluate our approach on multiple benchmark datasets where our perturbations can increase the D1-error (akin to fooling rate) of state-of-the-art stereo networks from 1% to as much as 87%. We investigate the effect of perturbations on the estimated scene geometry and identify object classes that are most vulnerable. Our analysis on the activations of registered points between left and right images led us to find architectural components that can increase robustness against adversaries. By simply designing networks with such components, one can reduce the effect of adversaries by up to 60.5%, which rivals the robustness of networks fine-tuned with costly adversarial data augmentation. Our design principle also improves their robustness against common image corruptions by an average of 70%.

Representing scenes with multiple semitransparent colored layers has been a popular and successful choice for real-time novel view synthesis. Existing approaches infer colors and transparency values over regularly spaced layers of planar or spherical shape. In this work, we introduce a new view synthesis approach based on multiple semitransparent layers with scene-adapted geometry. Our approach infers such representations from stereo pairs in two stages. The first stage produces the geometry of a small number of data-adaptive layers from a given pair of views. The second stage infers the color and transparency values for these layers, producing the final representation for novel view synthesis. Importantly, both stages are connected through a differentiable renderer and are trained end-to-end. In the experiments, we demonstrate the advantage of the proposed approach over the use of regularly spaced layers without adaptation to scene geometry. Despite being orders of magnitude faster during rendering, our approach also outperforms the recently proposed IBRNet system based on implicit geometry representation.

Neuromorphic cameras or event cameras mimic human vision by reporting changes in the intensity in a scene, instead of reporting the whole scene at once in a form of an image frame as performed by conventional cameras. Events are streamed data that are often dense when either the scene changes or the camera moves rapidly. The rapid movement causes the events to be overridden or missed when creating a tensor for the machine to learn on. To alleviate the event missing or overriding issue, we propose to learn to concentrate on the dense events to produce a compact event representation with high details for depth estimation. Specifically, we learn a model with events from both past and future but infer only with past data with the predicted future. We initially estimate depth in an event-only setting but also propose to further incorporate images and events by a hierarchical event and intensity combination network for better depth estimation. By experiments in challenging real-world scenarios, we validate that our method outperforms prior arts even with low computational cost. Code is available at: https://github.com/yonseivnl/se-cff.

Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into spatial and temporal convolutions separately, or computing self-attention along temporal dimension. The implicit assumption behind such successes is that the feature maps across consecutive frames can be nicely aggregated. Nevertheless, the assumption may not always hold especially for the regions with large deformation. In this paper, we present a new recipe of inter-frame attention block, namely Stand-alone Inter-Frame Attention (SIFA), that novelly delves into the deformation across frames to estimate local self-attention on each spatial location. Technically, SIFA remoulds the deformable design via re-scaling the offset predictions by the difference between two frames. Taking each spatial location in the current frame as the query, the locally deformable neighbors in the next frame are regarded as the keys/values. Then, SIFA measures the similarity between query and keys as stand-alone attention to weighted average the values for temporal aggregation. We further plug SIFA block into ConvNets and Vision Transformer, respectively, to devise SIFA-Net and SIFA-Transformer. Extensive experiments conducted on four video datasets demonstrate the superiority of SIFA-Net and SIFA-Transformer as stronger backbones. More remarkably, SIFA-Transformer achieves an accuracy of 83.1% on Kinetics-400 dataset. Source code is available at https://github.com/FuchenUSTC/SIFA.

Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph. Existing SGG approaches generally not only neglect the insufficient modality fusion between vision and language, but also fail to provide informative predicates due to the biased relationship predictions, leading SGG far from practical. Towards this end, in this paper, we first present a novel Stacked Hybrid-Attention network, which facilitates the intra-modal refinement as well as the inter-modal interaction, to serve as the encoder. We then devise an innovative Group Collaborative Learning strategy to optimize the decoder. Particularly, based upon the observation that the recognition capability of one classifier is limited towards an extremely unbalanced dataset, we first deploy a group of classifiers that are expert in distinguishing different subsets of classes, and then cooperatively optimize them from two aspects to promote the unbiased SGG. Experiments conducted on VG and GQA datasets demonstrate that, we not only establish a new state-of-the-art in the unbiased metric, but also nearly double the performance compared with two baselines. Our code is available at https://github.com/dongxingning/SHA-GCL-for-SGG.

Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-window based models. However, when inferring on long video sequences presenting low motion (i.e. in which some parts of the scene barely move), recurrent models diverge through recurrent processing, generating high frequency artifacts. To the best of our knowledge, no study about VSR pointed out this instability problem, which can be critical for some real-world applications. Video surveillance is a typical example where such artifacts would occur, as both the camera and the scene stay static for a long time. In this work, we expose instabilities of existing recurrent VSR networks on long sequences with low motion. We demonstrate it on a new long sequence dataset Quasi-Static Video Set, that we have created. Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory. We propose a new recurrent VSR network, coined Middle Recurrent Video Super-Resolution (MRVSR), based on this framework. We empirically show its competitive performance on long sequences with low motion.