CVPR 2022 论文列表

Real-world autonomous driving datasets comprise of images aggregated from different drives on the road. The ability to relight captured scenes to unseen lighting conditions, in a controllable manner, presents an opportunity to augment datasets with a richer variety of lighting conditions, similar to what would be encountered in the real-world. This paper presents a novel image-based relighting pipeline, SIMBAR, that can work with a single image as input. To the best of our knowledge, there is no prior work on scene relighting leveraging explicit geometric representations from a single image. We present qualitative comparisons with prior multi-view scene relighting baselines. To further validate and effectively quantify the benefit of leveraging SIMBAR for data augmentation for automated driving vision tasks, object detection and tracking experiments are conducted with a state-of-the-art method, a Multiple Object Tracking Accuracy (MOTA) of 93.3% is achieved with CenterTrack on SIMBAR-augmented KITTI - an impressive 9.0% relative improvement over the baseline MOTA of 85.6% with CenterTrack on original KITTI, both models trained from scratch and tested on Virtual KITTI. For more details and SIMBAR relit datasets, please visit our project website (https://simbarv1.github.io/).

Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous-driving systems. Existing image- and video-based driving datasets, however, fall short of capturing the mutable nature of the real world. In this paper, we introduce the largest synthetic dataset for autonomous driving, SHIFT. It presents discrete and continuous shifts in cloudiness, rain and fog intensity, time of day, and vehicle and pedestrian density. Featuring a comprehensive sensor suite and annotations for several mainstream perception tasks, SHIFT allows to investigate how a perception systems' performance degrades at increasing levels of domain shift, fostering the development of continuous adaptation strategies to mitigate this problem and assessing the robustness and generality of a model. Our dataset and benchmark toolkit are publicly available at https://www.vis.xyz/shift.

Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up two-stage or a point-based one-stage approach, which often suffers from high time complexity or sub-optimal designs. In this work, we propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem. To solve the problem, we develop a transformer-based end-to-end framework that first generates the entity and predicate proposal set, followed by inferring directed edges to form the relation triplets. In particular, we develop a new entity-aware predicate representation based on a structural predicate generator that leverages the compositional property of relationships. Moreover, we design a graph assembling module to infer the connectivity of the bipartite scene graph based on our entity-aware structure, enabling us to generate the scene graph in an end-to-end manner. Extensive experimental results show that our design is able to achieve the state-of-the-art or comparable performance on two challenging benchmarks, surpassing most of the existing approaches and enjoying higher efficiency in inference. We hope our model can serve as a strong baseline for the Transformer-based scene graph generation. Code is available in https://github.com/Scarecrow0/SGTR

Talking gesture generation is a practical yet challenging task which aims to synthesize gestures in line with speech. Gestures with meaningful signs can better convey useful information and arouse sympathy in the audience. Current works focus on aligning gestures with the speech rhythms, which are hard to mine the semantics and model semantic gestures explicitly. In this paper, we propose a novel method SEmantic Energized Generation (SEEG), for semantic-aware gesture generation. Our method contains two parts: DEcoupled Mining module (DEM) and Semantic Energizing Module (SEM). DEM decouples the semantic-irrelevant information from inputs and separately mines information for the beat and semantic gestures. SEM conducts semantic learning and produces semantic gestures. Apart from representational similarity, SEM requires the predictions to express the same semantics as the ground truth. Besides, a semantic prompter is designed in SEM to leverage the semantic-aware supervision to predictions. This promotes the networks to learn and generate semantic gestures. Experimental results reported in three metrics on different benchmarks prove that SEEG efficiently mines semantic cues and generates semantic gestures. In comparison, SEEG outperforms other methods in all semantic-aware evaluations on different datasets. Qualitative evaluations also indicate the superiority of SEEG in semantic expressiveness.

Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the training, and at most introduce the corresponding composite image as a single negative sample for an auxiliary constraint, which leads to limited distortion knowledge, and further causes a too large solution space, making the generated harmonized image distorted. Besides, none of them jointly constrain from the foreground self-style and foreground-background style consistency, which exacerbates this problem. Moreover, recent region-aware adaptive instance normalization achieves great success but only considers the global background feature distribution, making the aligned foreground feature distribution biased. To address these issues, we propose a self-consistent style contrastive learning scheme (SCS-Co). By dynamically generating multiple negative samples, our SCS-Co can learn more distortion knowledge and well regularize the generated harmonized image in the style representation space from two aspects of the foreground self-style and foreground-background style consistency, leading to a more photorealistic visual result. In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity. Experiments demonstrate the superiority of our method over other state-of-the-art methods in both quantitative comparison and visual analysis.

In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR. Firstly, we propose a second order spatial compatibility (SC^2) measure to compute the similarity between correspondences. It considers the global compatibility instead of local consistency, allowing for more distinctive clustering between inliers and outliers at early stage. Based on this measure, our registration pipeline employs a global spectral technique to find some reliable seeds from the initial correspondences. Then we design a two-stage strategy to expand each seed to a consensus set based on the SC^2 measure matrix. Finally, we feed each consensus set to a weighted SVD algorithm to generate a candidate rigid transformation and select the best model as the final result. Our method can guarantee to find a certain number of outlier-free consensus sets using fewer samplings, making the model estimation more efficient and robust. In addition, the proposed SC^2 measure is general and can be easily plugged into deep learning based frameworks. Extensive experiments are carried out to investigate the performance of our method.

We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.

Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the visual cues in RGB images, we rely on the shape information predominately from the depth (D) channel. The key idea is to explore the shape alignment of each instance against its corresponding category-level template shape, and the symmetric correspondence of each object category for estimating a coarse 3D object shape. Our framework deforms the point cloud of the category-level template shape to align the observed instance point cloud for implicitly representing its 3D rotation. Then we model the symmetric correspondence by predicting symmetric point cloud from the partially observed point cloud. The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation. Extensive experiments on the category-level NOCS benchmark demonstrate that our lightweight model still competes with state-of-the-art approaches that require labeled real-world images. We also deploy our approach to a physical Baxter robot to perform grasping tasks on unseen but category-known instances, and the results further validate the efficacy of our proposed model. Code and pre-trained models are available on the project webpage.

Rotation equivariance has recently become a strongly desired property in the 3D deep learning community. Yet most existing methods focus on equivariance regarding a global input rotation while ignoring the fact that rotation symmetry has its own spatial support. Specifically, we consider the object detection problem in 3D scenes, where an object bounding box should be equivariant regarding the object pose, independent of the scene motion. This suggests a new desired property we call object-level rotation equivariance. To incorporate object-level rotation equivariance into 3D object detectors, we need a mechanism to extract equivariant features with local object-level spatial support while being able to model cross-object context information. To this end, we propose Equivariant Object detection Network (EON) with a rotation equivariance suspension design to achieve object-level equivariance. EON can be applied to modern point cloud object detectors, such as VoteNet and PointRCNN, enabling them to exploit object rotation symmetry in scene-scale inputs. Our experiments on both indoor scene and autonomous driving datasets show that significant improvements are obtained by plugging our EON design into existing state-of-the-art 3D object detectors. Project website: https://kovenyu.com/EON/.

Concurrent perception datasets for autonomous driving are mainly limited to frontal view with sensors mounted on the vehicle. None of them is designed for the overlooked roadside perception tasks. On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system. To accelerate the progress of roadside perception, we present the first high-diversity challenging Roadside Perception 3D dataset- Rope3D from a novel view. The dataset consists of 50k images and over 1.5M 3D objects in various scenes, which are captured under different settings including various cameras with ambiguous mounting positions, camera specifications, viewpoints, and different environmental conditions. We conduct strict 2D-3D joint annotation and comprehensive data analysis, as well as set up a new 3D roadside perception benchmark with metrics and evaluation devkit. Furthermore, we tailor the existing frontal-view monocular 3D object detection approaches and propose to leverage the geometry constraint to solve the inherent ambiguities caused by various sensors, viewpoints. Our dataset is available on https://thudair.baai.ac.cn/rope.

Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimization framework. We further propose an effective and efficient instantiation of our approach, namely, Lattice Point Classifier (LPC), based on structured sparse coding in the permutohedral lattice and 2D convolutional neural networks (CNNs) that is end-to-end trainable. We demonstrate state-of-the-art robust point cloud classification performance on ModelNet40 and ScanNet under seven different attackers. For instance, we achieve 89.51% and 83.16% test accuracy on each dataset under the recent JGBA attacker that outperforms DUP-Net and IF-Defense with PointNet by 70%. Demo code is available at https://zhang-vislab.github.io.

Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image. In this study, we reveal the core challenges in this research area: how to synthesize robust region features (for unseen objects) that are as intra-class diverse and inter-class separable as the real samples, so that strong unseen object detectors can be trained upon them. To address these challenges, we build a novel zero-shot object detection framework that contains an Intra-class Semantic Diverging component and an Inter-class Structure Preserving component. The former is used to realize the one-to-more mapping to obtain diverse visual features from each class semantic vector, preventing miss-classifying the real unseen objects as image backgrounds. While the latter is used to avoid the synthesized features too scattered to mix up the inter-class and foreground-background relationship. To demonstrate the effectiveness of the proposed approach, comprehensive experiments on PASCAL VOC, COCO, and DIOR datasets are conducted. Notably, our approach achieves the new state-of-the-art performance on PASCAL VOC and COCO and it is the first study to carry out zero-shot object detection in remote sensing imagery.

Deep networks often make confident, yet, incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data. Yet, previous studies have shown that DGM likelihoods are unreliable and can be easily biased by simple transformations to input data. Here, we examine outlier detection with variational autoencoders (VAEs), among the simplest of DGMs. We propose novel analytical and algorithmic approaches to ameliorate key biases with VAE likelihoods. Our bias corrections are sample-specific, computationally inexpensive, and readily computed for various decoder visible distributions. Next, we show that a well-known image pre-processing technique -- contrast stretching -- extends the effectiveness of bias correction to further improve outlier detection. Our approach achieves state-of-the-art accuracies with nine grayscale and natural image datasets, and demonstrates significant advantages -- both with speed and performance -- over four recent, competing approaches. In summary, lightweight remedies suffice to achieve robust outlier detection with VAEs.

Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model invariant to small fluctuations in input data, our method helps models generalize to out-of-distribution samples and boosts model performance at test time. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks. FLAG is also highly flexible and scalable, and is deployable with arbitrary GNN backbones and large-scale datasets. We demonstrate the efficacy and stability of our method through extensive experiments and ablation studies. We also provide intuitive observations for a deeper understanding of our method. We open source our implementation at https://github.com/devnkong/FLAG.

Image steganography aims to hide secret images into a container image, where the secret is hidden from human vision and can be restored when necessary. Previous image steganography methods are limited in hiding capacity and robustness, commonly vulnerable to distortion on container images such as Gaussian noise, Poisson noise, and lossy compression. This paper presents a novel flow-based framework for robust invertible image steganography, dubbed as RIIS. We introduce the conditional normalizing flow to model the distribution of the redundant high-frequency component with the condition of the container image. Moreover, a well-designed container enhancement module (CEM) also contributes to the robust reconstruction. To regulate the network parameters for different distortion levels, we propose a distortion-guided modulation (DGM) over flow-based blocks to make it a one-size-fits-all model. In terms of both clean and distorted image steganography, extensive experiments reveal that the proposed RIIS efficiently improves the robustness while maintaining imperceptibility and capacity. As far as we know, we are the first learning-based scheme to enhance the robustness of image steganography in the literature. The guarantee of steganography robustness significantly broadens the application of steganography in real-world applications.

Model heterogeneous federated learning is a challenging task since each client independently designs its own model. Due to the annotation difficulty and free-riding participant issue, the local client usually contains unavoidable and varying noises, which cannot be effectively addressed by existing algorithms. This paper starts the first attempt to study a new and challenging robust federated learning problem with noisy and heterogeneous clients. We present a novel solution RHFL (Robust Heterogeneous Federated Learning), which simultaneously handles the label noise and performs federated learning in a single framework. It is featured in three aspects: (1) For the communication between heterogeneous models, we directly align the models feedback by utilizing public data, which does not require additional shared global models for collaboration. (2) For internal label noise, we apply a robust noise-tolerant loss function to reduce the negative effects. (3) For challenging noisy feedback from other participants, we design a novel client confidence re-weighting scheme, which adaptively assigns corresponding weights to each client in the collaborative learning stage. Extensive experiments validate the effectiveness of our approach in reducing the negative effects of different noise rates/types under both model homogeneous and heterogeneous federated learning settings, consistently outperforming existing methods.

Social presence, the feeling of being there with a "real" person, will fuel the next generation of communication systems driven by digital humans in virtual reality (VR). The best 3D video-realistic VR avatars that minimize the uncanny effect rely on person-specific (PS) models. However, these PS models are time-consuming to build and are typically trained with limited data variability, which results in poor generalization and robustness. Major sources of variability that affects the accuracy of facial expression transfer algorithms include using different VR headsets (e.g., camera configuration, slop of the headset), facial appearance changes over time (e.g., beard, make-up), and environmental factors (e.g., lighting, backgrounds). This is a major drawback for the scalability of these models in VR. This paper makes progress in overcoming these limitations by proposing an end-to-end multi-identity architecture (MIA) trained with specialized augmentation strategies. MIA drives the shape component of the avatar from three cameras in the VR headset (two eyes, one mouth), in untrained subjects, using minimal personalized information (i.e., neutral 3D mesh shape). Similarly, if the PS texture decoder is available, MIA is able to drive the full avatar (shape+texture) robustly outperforming PS models in challenging scenarios. Our key contribution to improve robustness and generalization, is that our method implicitly decouples, in an unsupervised manner, the facial expression from nuisance factors (e.g., headset, environment, facial appearance). We demonstrate the superior performance and robustness of the proposed method versus state-of-the-art PS approaches in a variety of experiments.

Contrastive learning relies on an assumption that positive pairs contain related views that share certain underlying information about an instance, e.g., patches of an image or co-occurring multimodal signals of a video. What if this assumption is violated? The literature suggests that contrastive learning produces suboptimal representations in the presence of noisy views, e.g., false positive pairs with no apparent shared information. In this work, we propose a new contrastive loss function that is robust against noisy views. We provide rigorous theoretical justifications by showing connections to robust symmetric losses for noisy binary classification and by establishing a new contrastive bound for mutual information maximization based on the Wasserstein distance measure. The proposed loss is completely modality-agnostic and a simple drop-in replacement for the InfoNCE loss, which makes it easy to apply to existing contrastive frameworks. We show that our approach provides consistent improvements over the state-of-the-art on image, video, and graph contrastive learning benchmarks that exhibit a variety of real-world noise patterns.

We consider distributed (gradient descent-based) learning scenarios where the server combines the gradients of learning objectives gathered from local clients. As individual data collection and learning environments can vary, some clients could transfer erroneous gradients e.g., due to adversarial data or gradient perturbations. Further, for data privacy and security, the identities of such affected clients are often unknown to the server. In such cases, naively aggregating the resulting gradients can mislead the learning process. We propose a new server-side learning algorithm that robustly combines gradients. Our algorithm embeds the local gradients into the manifold of normalized gradients and refines their combinations via simulating a diffusion process therein. The resulting algorithm is instantiated as a computationally simple and efficient weighted gradient averaging algorithm. In the experiments with five classification and three regression benchmark datasets, our algorithm demonstrated significant performance improvements over existing robust gradient combination algorithms as well as the baseline uniform gradient averaging algorithm.