CVPR 2023 Papers

Rolling shutter correction (RSC) is becoming increasingly popular for RS cameras that are widely used in commercial and industrial applications. Despite the promising performance, existing RSC methods typically employ a two-stage network structure that ignores intrinsic information interactions and hinders fast inference. In this paper, we propose a single-stage encoder-decoder-based network, named JAMNet, for efficient RSC. It first extracts pyramid features from consecutive RS inputs, and then simultaneously refines the two complementary information (i.e., global shutter appearance and undistortion motion field) to achieve mutual promotion in a joint learning decoder. To inject sufficient motion cues for guiding joint learning, we introduce a transformer-based motion embedding module and propose to pass hidden states across pyramid levels. Moreover, we present a new data augmentation strategy "vertical flip + inverse order" to release the potential of the RSC datasets. Experiments on various benchmarks show that our approach surpasses the state-of-the-art methods by a large margin, especially with a 4.7 dB PSNR leap on real-world RSC. Code is available at https://github.com/GitCVfb/JAMNet.

Real-world adversarial physical patches were recently shown to be successful in compromising state-of-the-art models in a variety of computer vision applications. The most promising defenses that are based on either input gradient or features analyses have been shown to be compromised by recent GAN-based adaptive attacks that generate realistic/naturalistic patches. In this paper, we propose Jedi, a new defense against adversarial patches that is resilient to realistic patch attacks, and also improves detection and recovery compared to the state of the art. Jedi leverages two new ideas: (1) it improves the identification of potential patch regions using entropy analysis: we show that the entropy of adversarial patches is high, even in naturalistic patches; and (2) it improves the localization of adversarial patches, using an autoencoder that is able to complete patch regions and filter out normal regions with high entropy that are not part of a patch. Jedi achieves high precision adversarial patch localization, which we show is critical to successfully repair the images. Since Jedi relies on an input entropy analysis, it is model-agnostic, and can be applied on pre-trained off-the-shelf models without changes to the training or inference of the protected models. Jedi detects on average 90% of adversarial patches across different benchmarks and recovers up to 94% of successful patch attacks (Compared to 75% and 65% for LGS and Jujutsu, respectively). Jedi is also able to continue detection even in the presence of adaptive realistic patches that are able to fool other defenses.

Autonomous robotic systems operating in human environments must understand their surroundings to make accurate and safe decisions. In crowded human scenes with close-up human-robot interaction and robot navigation, a deep understanding of surrounding people requires reasoning about human motion and body dynamics over time with human body pose estimation and tracking. However, existing datasets captured from robot platforms either do not provide pose annotations or do not reflect the scene distribution of social robots. In this paper, we introduce JRDB-Pose, a large-scale dataset and benchmark for multi-person pose estimation and tracking. JRDB-Pose extends the existing JRDB which includes videos captured from a social navigation robot in a university campus environment, containing challenging scenes with crowded indoor and outdoor locations and a diverse range of scales and occlusion types. JRDB-Pose provides human pose annotations with per-keypoint occlusion labels and track IDs consistent across the scene and with existing annotations in JRDB. We conduct a thorough experimental study of state-of-the-art multi-person pose estimation and tracking methods on JRDB-Pose, showing that our dataset imposes new challenges for the existing methods. JRDB-Pose is available at https://jrdb.erc.monash.edu/.

Representing visual signals with implicit coordinate-based neural networks, as an effective replacement of the traditional discrete signal representation, has gained considerable popularity in computer vision and graphics. In contrast to existing implicit neural representations which focus on modelling the scene only, this paper proposes a novel implicit camera model which represents the physical imaging process of a camera as a deep neural network. We demonstrate the power of this new implicit camera model on two inverse imaging tasks: i) generating all-in-focus photos, and ii) HDR imaging. Specifically, we devise an implicit blur generator and an implicit tone mapper to model the aperture and exposure of the camera's imaging process, respectively. Our implicit camera model is jointly learned together with implicit scene models under multi-focus stack and multi-exposure bracket supervision. We have demonstrated the effectiveness of our new model on large number of test images and videos, producing accurate and visually appealing all-in-focus and high dynamic range images. In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.

Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve surface correspondences across different poses. In this work, we introduce Invertible Neural Skinning (INS) to address these shortcomings. To maintain correspondences, we propose a Pose-conditioned Invertible Network (PIN) architecture, which extends the LBS process by learning additional pose-varying deformations. Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline. We demonstrate the strong performance of our method by outperforming the state-of-the-art reposing techniques on clothed humans and preserving surface correspondences, while being an order of magnitude faster. We also perform an ablation study, which shows the usefulness of our pose-conditioning formulation, and our qualitative results display that INS can rectify artefacts introduced by LBS well.

In this work, we propose an inverse rendering model that estimates 3D shape, spatially-varying reflectance, homogeneous subsurface scattering parameters, and an environment illumination jointly from only a pair of captured images of a translucent object. In order to solve the ambiguity problem of inverse rendering, we use a physically-based renderer and a neural renderer for scene reconstruction and material editing. Because two renderers are differentiable, we can compute a reconstruction loss to assist parameter estimation. To enhance the supervision of the proposed neural renderer, we also propose an augmented loss. In addition, we use a flash and no-flash image pair as the input. To supervise the training, we constructed a large-scale synthetic dataset of translucent objects, which consists of 117K scenes. Qualitative and quantitative results on both synthetic and real-world datasets demonstrated the effectiveness of the proposed model.

We introduce a new family of deep neural networks. Instead of the conventional representation of network layers as N-dimensional weight tensors, we use continuous layer representation along the filter and channel dimensions. We call such networks Integral Neural Networks (INNs). In particular, the weights of INNs are represented as continuous functions defined on N-dimensional hypercubes, and the discrete transformations of inputs to the layers are replaced by continuous integration operations, accordingly. During the inference stage, our continuous layers can be converted into the traditional tensor representation via numerical integral quadratures. Such kind of representation allows the discretization of a network to an arbitrary size with various discretization intervals for the integral kernels. This approach can be applied to prune the model directly on the edge device while featuring only a small performance loss at high rates of structural pruning without any fine-tuning. To evaluate the practical benefits of our proposed approach, we have conducted experiments using various neural network architectures for multiple tasks. Our reported results show that the proposed INNs achieve the same performance with their conventional discrete counterparts, while being able to preserve approximately the same performance (2 % accuracy loss for ResNet18 on Imagenet) at a high rate (up to 30%) of structural pruning without fine-tuning, compared to 65 % accuracy loss of the conventional pruning methods under the same conditions.

Recently, semi-supervised semantic segmentation has achieved promising performance with a small fraction of labeled data. However, most existing studies treat all unlabeled data equally and barely consider the differences and training difficulties among unlabeled instances. Differentiating unlabeled instances can promote instance-specific supervision to adapt to the model's evolution dynamically. In this paper, we emphasize the cruciality of instance differences and propose an instance-specific and model-adaptive supervision for semi-supervised semantic segmentation, named iMAS. Relying on the model's performance, iMAS employs a class-weighted symmetric intersection-over-union to evaluate quantitative hardness of each unlabeled instance and supervises the training on unlabeled data in a model-adaptive manner. Specifically, iMAS learns from unlabeled instances progressively by weighing their corresponding consistency losses based on the evaluated hardness. Besides, iMAS dynamically adjusts the augmentation for each instance such that the distortion degree of augmented instances is adapted to the model's generalization capability across the training course. Not integrating additional losses and training procedures, iMAS can obtain remarkable performance gains against current state-of-the-art approaches on segmentation benchmarks under different semi-supervised partition protocols.

Recently, indiscernible scene understanding has attracted a lot of attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. For benchmarking purposes, we select 14 mainstream methods for object counting and carefully evaluate them on IOCfish5K. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. Experiments show that IOCFormer achieves state-of-the-art scores on IOCfish5K.

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of these models are very high, the top-1 accuracies are much lower (over 25% gap in some cases). We investigate the reasons for this performance gap and find that many of the failure cases are caused by ambiguity in the text prompts. First, we develop a simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations. We show that our procedure better predicts mistakes, outperforming the popular max logit baseline on selective prediction tasks. Next, we propose a simple and efficient way to improve accuracy on such uncertain images by making use of the WordNet hierarchy; specifically we augment the original class by incorporating its parent and children from the semantic label hierarchy, and plug the augmentation into text prompts. We conduct experiments on both CLIP and LiT models with five different ImageNet- based datasets. For CLIP, our method improves the top-1 accuracy by 17.13% on the uncertain subset and 3.6% on the entire ImageNet validation set. We also show that our method improves across ImageNet shifted datasets, four other datasets, and other model architectures such as LiT. Our proposed method is hyperparameter-free, requires no additional model training and can be easily scaled to other large multi-modal architectures. Code is available at https://github.com/gyhandy/Hierarchy-CLIP.

Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional dataset condensation methods are optimization-oriented and condense the dataset by performing gradient or parameter matching during model optimization, which is computationally intensive even on small datasets and models. In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising. Specifically, we identify two important shortcomings of naive distribution matching (i.e., imbalanced feature numbers and unvalidated embeddings for distance computation) and address them with three novel techniques (i.e., partitioning and expansion augmentation, efficient and enriched model sampling, and class-aware distribution regularization). Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources, thereby scaling data condensation to larger datasets and models. Extensive experiments demonstrate the effectiveness of our method. Codes are available at https://github.com/uitrbn/IDM

Previous methods solve feature matching and pose estimation using a two-stage process by first finding matches and then estimating the pose. As they ignore the geometric relationships between the two tasks, they focus on either improving the quality of matches or filtering potential outliers, leading to limited efficiency or accuracy. In contrast, we propose an iterative matching and pose estimation framework (IMP) leveraging the geometric connections between the two tasks: a few good matches are enough for a roughly accurate pose estimation; a roughly accurate pose can be used to guide the matching by providing geometric constraints. To this end, we implement a geometry-aware recurrent module with transformers which jointly outputs sparse matches and camera poses. Specifically, for each iteration, we first implicitly embed geometric information into the module via a pose-consistency loss, allowing it to predict geometry-aware matches progressively. Second, we introduce an efficient IMP (EIMP) to dynamically discard keypoints without potential matches, avoiding redundant updating and significantly reducing the quadratic time complexity of attention computation in transformers. Experiments on YFCC100m, Scannet, and Aachen Day-Night datasets demonstrate that the proposed method outperforms previous approaches in terms of accuracy and efficiency.

Humans have long been recorded in a variety of forms since antiquity. For example, sculptures and paintings were the primary media for depicting human beings before the invention of cameras. However, most current human-centric computer vision tasks like human pose estimation and human image generation focus exclusively on natural images in the real world. Artificial humans, such as those in sculptures, paintings, and cartoons, are commonly neglected, making existing models fail in these scenarios. As an abstraction of life, art incorporates humans in both natural and artificial scenes. We take advantage of it and introduce the Human-Art dataset to bridge related tasks in natural and artificial scenarios. Specifically, Human-Art contains 50k high-quality images with over 123k person instances from 5 natural and 15 artificial scenarios, which are annotated with bounding boxes, keypoints, self-contact points, and text information for humans represented in both 2D and 3D. It is, therefore, comprehensive and versatile for various downstream tasks. We also provide a rich set of baseline results and detailed analyses for related tasks, including human detection, 2D and 3D human pose estimation, image generation, and motion transfer. As a challenging dataset, we hope Human-Art can provide insights for relevant research and open up new research questions.

In this paper, we investigate how to complete human body shape models by combining shape and flow estimation given two consecutive depth images. Shape completion is a challenging task in computer vision that is highly under-constrained when considering partial depth observations. Besides model based strategies that exploit strong priors, and consequently struggle to preserve fine geometric details, learning based approaches build on weaker assumptions and can benefit from efficient implicit representations. We adopt such a representation and explore how the motion flow between two consecutive frames can contribute to the shape completion task. In order to effectively exploit the flow information, our architecture combines both estimations and implements two features for robustness: First, an all-to-all attention module that encodes the correlation between points in the same frame and between corresponding points in different frames; Second, a coarse-dense to fine-sparse strategy that balances the representation ability and the computational cost. Our experiments demonstrate that the flow actually benefits human body model completion. They also show that our method outperforms the state-of-the-art approaches for shape completion on 2 benchmarks, considering different human shapes, poses, and clothing.

Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear often among the nearest neighbors of points from another class, degrading the classifier's performance. To address the hubness problem in FSL, we first prove that hubness can be eliminated by distributing representations uniformly on the hypersphere. We then propose two new approaches to embed representations on the hypersphere, which we prove optimize a tradeoff between uniformity and local similarity preservation -- reducing hubness while retaining class structure. Our experiments show that the proposed methods reduce hubness, and significantly improves transductive FSL accuracy for a wide range of classifiers.

Monocular 3D human pose and shape estimation is an ill-posed problem since multiple 3D solutions can explain a 2D image of a subject. Recent approaches predict a probability distribution over plausible 3D pose and shape parameters conditioned on the image. We show that these approaches exhibit a trade-off between three key properties: (i) accuracy - the likelihood of the ground-truth 3D solution under the predicted distribution, (ii) sample-input consistency - the extent to which 3D samples from the predicted distribution match the visible 2D image evidence, and (iii) sample diversity - the range of plausible 3D solutions modelled by the predicted distribution. Our method, HuManiFlow, predicts simultaneously accurate, consistent and diverse distributions. We use the human kinematic tree to factorise full body pose into ancestor-conditioned per-body-part pose distributions in an autoregressive manner. Per-body-part distributions are implemented using normalising flows that respect the manifold structure of SO(3), the Lie group of per-body-part poses. We show that ill-posed, but ubiquitous, 3D point estimate losses reduce sample diversity, and employ only probabilistic training losses. HuManiFlow outperforms state-of-the-art probabilistic approaches on the 3DPW and SSP-3D datasets.

Movie story analysis requires understanding characters' emotions and mental states. Towards this goal, we formulate emotion understanding as predicting a diverse and multi-label set of emotions at the level of a movie scene and for each character. We propose EmoTx, a multimodal Transformer-based architecture that ingests videos, multiple characters, and dialog utterances to make joint predictions. By leveraging annotations from the MovieGraphs dataset, we aim to predict classic emotions (e.g. happy, angry) and other mental states (e.g. honest, helpful). We conduct experiments on the most frequently occurring 10 and 25 labels, and a mapping that clusters 181 labels to 26. Ablation studies and comparison against adapted state-of-the-art emotion recognition approaches shows the effectiveness of EmoTx. Analyzing EmoTx's self-attention scores reveals that expressive emotions often look at character tokens while other mental states rely on video and dialog cues.

Deep learning with noisy labels is challenging and inevitable in many circumstances. Existing methods reduce the impact of noise samples by reducing loss weights of uncertain samples or by filtering out potential noise samples, which highly rely on the model's superior discriminative power for identifying noise samples. However, in the training stage, the trainee model is imperfect will miss many noise samples, which cause continuous damage to the model training. Consequently, there is a large performance gap between existing anti-noise models trained with noisy samples and models trained with clean samples. In this paper, we put forward a Gradient Switching Strategy (GSS) to prevent the continuous damage of noise samples to the classifier. Theoretical analysis shows that the damage comes from the misleading gradient direction computed from the noise samples. The trainee model will deviate from the correct optimization direction under the influence of the accumulated misleading gradient of noise samples. To address this problem, the proposed GSS alleviates the damage by switching the current gradient direction of each sample to a new direction selected from a gradient direction pool, which contains all-class gradient directions with different probabilities. During training, the trainee model is optimized along switched gradient directions generated by GSS, which assigns higher probabilities to potential principal directions for high-confidence samples. Conversely, uncertain samples have a relatively uniform probability distribution for all gradient directions, which can cancel out the misleading gradient directions. Extensive experiments show that a model trained with GSS can achieve comparable performance with a model trained with clean data. Moreover, the proposed GSS is pluggable for existing frameworks for noisy-label learning. This work can provide a new perspective for future noisy-label learning.

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.