CVPR 2022 论文列表

Learning a unified person detection and re-identification model is a key component of modern trackers. However, training such models usually relies on the availability of training images / videos that are manually labeled with both person boxes and their identities. In this work, we explore training such a model by only using person box annotations, thus removing the necessity of manually labeling a training dataset with additional person identity annotation as these are expensive to collect. To this end, we present a contrastive learning framework to learn person similarity without using manually labeled identity annotations. First, we apply image-level augmentation to images on public person detection datasets, based on which we learn a strong model for general person detection as well as for short-term person re-identification. To learn a model capable of longer-term re-identification, we leverage the natural appearance evolution of each person in videos to serve as instance-level appearance augmentation in our contrastive loss formulation. Without access to the target dataset or person identity annotation, our model achieves competitive results compared to existing fully-supervised state-of-the-art methods on both person search and person tracking tasks. Our model also shows promising results for saving the annotation cost that is needed to achieve a certain level of performance on the person search task.

State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. In this paper, we attempt to unfold an important factor that hinders the networks from generalizing across domains: through the lens of shortcut learning. We demonstrate that the learning of feature representations in stereo matching networks is heavily influenced by synthetic data artefacts (shortcut attributes). To mitigate this issue, we propose an Information-Theoretic Shortcut Avoidance (ITSA) approach to automatically restrict shortcut-related information from being encoded into the feature representations. As a result, our proposed method learns robust and shortcut-invariant features by minimizing the sensitivity of latent features to input variations. To avoid the prohibitive computational cost of direct input sensitivity optimization, we propose an effective yet feasible algorithm to achieve robustness. We show that using this method, state-of-the-art stereo matching networks that are trained purely on synthetic data can effectively generalize to challenging and previously unseen real data scenarios. Importantly, the proposed method enhances the robustness of the synthetic trained networks to the point that they outperform their fine-tuned counterparts (on real data) for challenging out-of-domain stereo datasets.

Infrared small target detection (IRSTD) refers to extracting small and dim targets from blurred backgrounds, which has a wide range of applications such as traffic management and marine rescue. Due to the low signal-to-noise ratio and low contrast, infrared targets are easily submerged in the background of heavy noise and clutter. How to detect the precise shape information of infrared targets remains challenging. In this paper, we propose a novel infrared shape network (ISNet), where Taylor finite difference (TFD)-inspired edge block and two-orientation attention aggregation (TOAA) block are devised to address this problem. Specifically, TFD-inspired edge block aggregates and enhances the comprehensive edge information from different levels, in order to improve the contrast between target and background and also lay a foundation for extracting shape information with mathematical interpretation. TOAA block calculates the low-level information with attention mechanism in both row and column directions and fuses it with the high-level information to capture the shape characteristic of targets and suppress noises. In addition, we construct a new benchmark consisting of 1,000 realistic images in various target shapes, different target sizes, and rich clutter backgrounds with accurate pixel-level annotations, called IRSTD-1k. Experiments on public datasets and IRSTD-1k demonstrate the superiority of our approach over representative state-of-the-art IRSTD methods. The dataset and code are available at github.com/RuiZhang97/ISNet.

Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the inductive bias the network imposes in the DIP framework depends on the architecture. Therefore, researchers have studied how to automate the search to determine the best-performing model. However, common neural architecture search (NAS) techniques are resource and time-intensive. Moreover, best-performing models are determined for a whole dataset of images instead of for each image independently, which would be prohibitively expensive. In this work, we first show that optimal neural architectures in the DIP framework are image-dependent. Leveraging this insight, we then propose an image-specific NAS strategy for the DIP framework that requires substantially less training than typical NAS approaches, effectively enabling image-specific NAS. We justify the proposed strategy's effectiveness by (1) demonstrating its performance on a NAS Dataset for DIP that includes 522 models from a particular search space (2) conducting extensive experiments on image denoising, inpainting, and super-resolution tasks. Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration. Codes and datasets are available at https://github.com/ozgurkara99/ISNAS-DIP.

The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation. To tackle these issues, most of the previous works follow the global-local refinement pipeline, which pays more attention to the memory consumption but neglects the inference speed. In comparison to the pipeline that partitions the large image into small local regions, we focus on inferring the whole image directly. In this paper, we propose ISDNet, a novel ultra-high resolution segmentation framework that integrates the shallow and deep networks in a new manner, which significantly accelerates the inference speed while achieving accurate segmentation. To further exploit the relationship between the shallow and deep features, we propose a novel Relational-Aware feature Fusion module, which ensures high performance and robustness of our framework. Extensive experiments on Deepglobe, Inria Aerial, and Cityscapes datasets demonstrate our performance is consistently superior to state-of-the-arts. Specifically, it achieves 73.30 mIoU with a speed of 27.70 FPS on Deepglobe, which is more accurate and 172 x faster than the recent competitor. Code available at https://github.com/cedricgsh/ISDNet.

We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. Our method adopts neural representations for geometry as signed distance fields (SDFs) and materials during optimization to enjoy their flexibility and compactness, and features a hybrid optimization scheme for neural SDFs: first, optimize using a volumetric radiance field approach to recover correct topology, then optimize further using edge-aware physics-based surface rendering for geometry refinement and disentanglement of materials and lighting. In the second stage, we also draw inspiration from mesh-based differentiable rendering, and design a novel edge sampling algorithm for neural SDFs to further improve performance. We show that our IRON achieves significantly better inverse rendering quality compared to prior works.

Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, \Ours , that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released at https://github.com/ViLab-UCSD/IRISformer

We propose INS-Conv, an INcremental Sparse Convolutional network which enables online accurate 3D semantic and instance segmentation. Benefiting from the incremental nature of RGB-D reconstruction, we only need to update the residuals between the reconstructed scenes of consecutive frames, which are usually sparse. For layer design, we define novel residual propagation rules for sparse convolution operations, achieving close approximation to standard sparse convolution. For network architecture, an uncertainty term is proposed to adaptively select which residual to update, further improving the inference accuracy and efficiency. Based on INS-Conv, an online joint 3D semantic and instance segmentation pipeline is proposed, reaching an inference speed of 15 FPS on GPU and 10 FPS on CPU. Experiments on ScanNetv2 and SceneNN datasets show that the accuracy of our method surpasses previous online methods by a large margin, and is on par with state-of-the-art offline methods. A live demo on portable devices further shows the superior performance of INS-Conv.

Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications. In this work, we devise an efficient encoder-decoder based network, termed IFRNet, for fast intermediate frame synthesizing. It first extracts pyramid features from given inputs, and then refines the bilateral intermediate flow fields together with a powerful intermediate feature until generating the desired output. The gradually refined intermediate feature can not only facilitate intermediate flow estimation, but also compensate for contextual details, making IFRNet do not need additional synthesis or refinement module. To fully release its potential, we further propose a novel task-oriented optical flow distillation loss to focus on learning the useful teacher knowledge towards frame synthesizing. Meanwhile, a new geometry consistency regularization term is imposed on the gradually refined intermediate features to keep better structure layout. Experiments on various benchmarks demonstrate the excellent performance and fast inference speed of proposed approaches. Code is available at https://github.com/ltkong218/IFRNet.

Accurate object rearrangement from vision is a crucial problem for a wide variety of real-world robotics applications in unstructured environments. We propose IFOR, Iterative Flow Minimization for Robotic Object Rearrangement, an end-to-end method for the challenging problem of object rearrangement for unknown objects given an RGBD image of the original and final scenes. First, we learn an optical flow model based on RAFT to estimate the relative transformation of the objects purely from synthetic data. This flow is then used in an iterative minimization algorithm to achieve accurate positioning of previously unseen objects. Crucially, we show that our method applies to cluttered scenes, and in the real world, while training only on synthetic data. Videos are available at https://imankgoyal.github.io/ifor.html.

The lack of large-scale noisy-clean image pairs restricts supervised denoising methods' deployment in actual applications. While existing unsupervised methods are able to learn image denoising without ground-truth clean images, they either show poor performance or work under impractical settings (e.g., paired noisy images). In this paper, we present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. It performs two steps iteratively: (1) Constructing a noisier-noisy dataset with random noise from the noise model; (2) training a model on the noisier-noisy dataset and using the trained model to refine noisy images to obtain the targets used in the next round. We further approximate our full iterative method with a fast algorithm for more efficient training while keeping its original high performance. Experiments on real-world, synthetic, and correlated noise show that our proposed unsupervised denoising approach has superior performances over existing unsupervised methods and competitive performance with supervised methods. In addition, we argue that existing denoising datasets are of low quality and contain only a small number of scenes. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes. The dataset can serve as a strong benchmark for better evaluating raw image denoising. Code and dataset will be released at https://github.com/zhangyi-3/IDR

This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregularity and under-sampling are two major challenges. To tackle the challenges, we propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. Specifically, we propose a temporal consistency learning module to align two consecutive point cloud frames point-wisely, based on which we can employ linear interpolation to obtain coarse trajectories/in-between frames. To compensate the high-order nonlinear components of trajectories, we apply aligned feature embeddings that encode local geometry properties to regress point-wise increments, which are combined with the coarse estimations. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually. Our framework can bring benefits to 3D motion data acquisition. The source code is publicly available at https://github.com/ZENGYIMING-EAMON/IDEA-Net.git.

Current methods for learning realistic and animatable 3D clothed avatars need either posed 3D scans or 2D images with carefully controlled user poses. In contrast, our goal is to learn the avatar from only 2D images of people in unconstrained poses. Given a set of images, our method estimates a detailed 3D surface from each image and then combines these into an animatable avatar. Implicit functions are well suited to the first task, as they can capture details like hair or clothes. Current methods, however, are not robust to varied human poses and often produce 3D surfaces with broken or disembodied limbs, missing details, or non-human shapes. The problem is that these methods use global feature encoders that are sensitive to global pose. To address this, we propose ICON ("Implicit Clothed humans Obtained from Normals"), which uses local features. ICON has two main modules, both of which exploit the SMPL body model. First, ICON infers detailed clothed-human normals(front/back) conditioned on the SMPL normals. Second, a visibility-aware implicit surface regressor produces an iso-surface of the human occupancy field. Importantly, at inference time, a feedback loop alternates between refining the SMPL mesh using the inferred clothed normals and then refining the normals. Given multiple reconstructed frames of a subject in varied poses, we use modified SCANimate to produce an animatable avatar from them. Evaluation on the AGORA and CAPE datasets shows that ICON outperforms the state-of-the-art in reconstruction, even with heavily limited training data. Additionally, it is much more robust to out-of-distribution samples, e.g., in-the-wild poses/images and out-of-frame cropping. ICON takes a step towards pose-robust 3D clothed human reconstruction from in-the-wild images. This enables creating avatars directly from video with personalized and nature pose-dependent cloth deformation. Our models and code will be available for research.

Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details. Neural volumetric representations approach photorealism but are hard to animate and do not generalize well to unseen expressions. To tackle this problem, we propose IMavatar (Implicit Morphable avatar), a novel method for learning implicit head avatars from monocular videos. Inspired by the fine-grained control mechanisms afforded by conventional 3DMMs, we represent the expression- and pose- related deformations via learned blendshapes and skinning fields. These attributes are pose-independent and can be used to morph the canonical geometry and texture fields given novel expression and pose parameters. We employ ray marching and iterative root-finding to locate the canonical surface intersection for each pixel. A key contribution is our novel analytical gradient formulation that enables end- to-end training of IMavatars from videos. We show quantitatively and qualitatively that our method improves geometry and covers a more complete expression space compared to state-of-the-art methods. Code and data can be found at https://ait.ethz.ch/projects/2022/IMavatar/.

Recent advances in contrastive learning have enlightened diverse applications across various semi-supervised fields. Jointly training supervised learning and unsupervised learning with a shared feature encoder becomes a common scheme. Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier. In this work, we systematically explore the relationship between self-supervised learning and supervised learning, and study how self-supervised learning helps robust data-efficient deep learning. We propose hyperspherical consistency regularization (HCR), a simple yet effective plug-and-play method, to regularize the classifier using feature-dependent information and thus avoid bias from labels. Specifically, HCR first project logits from the classifier and feature projections from the projection head on the respective hypersphere, then it enforces data points on hyperspheres to have similar structures by minimizing binary cross entropy of pairwise distances' similarity metrics. Extensive experiments on semi-supervised learning and weakly-supervised learning demonstrate the effectiveness of our proposed method, by showing superior performance with HCR.

In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling. We formulate deep metric learning as a hypergraph node classification problem in which each sample in a mini-batch is regarded as a node and each hyperedge models class-specific semantic relations represented by a semantic tuplet. Unlike previous graph-based losses that only use a bundle of pairwise relations, our HIST loss takes advantage of the multilateral semantic relations provided by the semantic tuplets through hypergraph modeling. Notably, by leveraging the rich multilateral semantic relations, HIST loss guides the embedding model to learn class-discriminative visual semantics, contributing to better generalization performance and model robustness against input corruptions. Extensive experiments and ablations provide a strong motivation for the proposed method and show that our HIST loss leads to improved feature learning, achieving state-of-the-art results on three widely used benchmarks. Code is available at https://github.com/ljin0429/HIST.

Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations -- usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric.

For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes. In this work, we show that hyperbolic manifolds provide a valuable alternative for image segmentation and propose a tractable formulation of hierarchical pixel-level classification in hyperbolic space. Hyperbolic Image Segmentation opens up new possibilities and practical benefits for segmentation, such as uncertainty estimation and boundary information for free, zero-label generalization, and increased performance in low-dimensional output embeddings.

Pansharpening aims to fuse a registered high-resolution panchromatic image (PAN) with a low-resolution hyperspectral image (LR-HSI) to generate an enhanced HSI with high spectral and spatial resolution. Existing pansharpening approaches neglect using an attention mechanism to transfer HR texture features from PAN to LR-HSI features, resulting in spatial and spectral distortions. In this paper, we present a novel attention mechanism for pansharpening called HyperTransformer, in which features of LR-HSI and PAN are formulated as queries and keys in a transformer, respectively. HyperTransformer consists of three main modules, namely two separate feature extractors for PAN and HSI, a multi-head feature soft attention module, and a spatial-spectral feature fusion module. Such a network improves both spatial and spectral quality measures of the pansharpened HSI by learning cross-feature space dependencies and long-range details of PAN and LR-HSI. Furthermore, HyperTransformer can be utilized across multiple spatial scales at the backbone for obtaining improved performance. Extensive experiments conducted on three widely used datasets demonstrate that HyperTransformer achieves significant improvement over the state-of-the-art methods on both spatial and spectral quality measures. Implementation code and pre-trained weights can be accessed at https://github.com/wgcban/HyperTransformer.