ECCV 2020 论文列表

Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignoring semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. Specifically, we develop a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuses semantic information and multi-view information respectively. We also propose a new stereo based rainy datasets for benchmarking. Experiments on both monocular and the newly proposed stereo rainy datasets demonstrate that the proposed method achieves the state-of-the-art performance."

In modern computer vision, images are typically represented as a fixed uniform grid with some stride and processed via a deep convolutional neural network. We argue that deforming the grid to better align with the high-frequency image content is a more effective strategy. We introduce mph{Deformable Grid} (Defgrid), a learnable neural network module that predicts location offsets of vertices of a 2-dimensional triangular grid such that the edges of the deformed grid align with image boundaries. We showcase our Defgrid in a variety of use cases, i.e., by inserting it as a module at various levels of processing. We utilize Defgrid as an end-to-end mph{learnable geometric downsampling} layer that replaces standard pooling methods for reducing feature resolution when feeding images into a deep CNN. We show significantly improved results at the same grid resolution compared to using CNNs on uniform grids for the task of semantic segmentation. We also utilize Defgrid at the output layers for the task of object mask annotation, and show that reasoning about object boundaries on our predicted polygonal grid leads to more accurate results over existing pixel-wise and curve-based approaches. We finally showcase DefGrid as a standalone module for unsupervised image segmentation, showing superior performance over existing superpixel-based approaches. Project website: http://www.cs.toronto.edu/~jungao/def-grid ."

Long-term camera re-localization is an important task with numerous computer vision and robotics applications. Whilst various outdoor benchmarks exist that target lighting, weather and seasonal changes, far less attention has been paid to appearance changes that occur indoors. This has led to a mismatch between popular indoor benchmarks, which focus on static scenes, and indoor environments that are of interest for many real-world applications. In this paper, we adapt 3RScan -- a recently introduced indoor RGB-D dataset designed for object instance re-localization -- to create RIO10, a new long-term camera re-localization benchmark focused on indoor scenes. We propose new metrics for evaluating camera re-localization and explore how state-of-the-art camera re-localizers perform according to these metrics. We also examine in detail how different types of scene change affect the performance of different methods, based on novel ways of detecting such changes in a given RGB-D frame. Our results clearly show that long-term indoor re-localization is an unsolved problem. Our benchmark and tools are publicly available at waldjohannau.github.io/RIO10"

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space. As a result, the reconstruction results lose the fine-grained geometry and look different from real faces. To alleviate this issue, we first propose a solution to construct large-scale fine-grained 3D data from RGB-D images, which are expected to be massively collected as the proceeding of hand-held depth camera. A new dataset Fine-Grained 3D face (FG3D) with 200k samples is constructed to provide sufficient data for neural network training. Secondly, we propose a Fine-Grained reconstruction Network (FGNet) that can concentrate on shape modification by warping the network input and output to the UV space. Through FG3D and FGNet, we successfully generate reconstruction results with fine-grained geometry. The experiments on several benchmarks validate the effectiveness of our method compared to several baselines and other state-of-the-art methods. "

Recent Transformer-based large-scale pre-trained models have revolutionized vision-and-language (V+L) research. Models such as ViLBERT, LXMERT and UNITER have significantly lifted state of the art across a wide range of V+L benchmarks. However, little is known about the inner mechanisms that destine their impressive success. To reveal the secrets behind the scene, we present VALUE (Vision-And-Language Understanding Evaluation), a set of meticulously designed probing tasks (e.g., Visual Coreference Resolution, Visual Relation Detection) generalizable to standard pre-trained V+L models, to decipher the inner workings of multimodal pre-training (e.g., implicit knowledge garnered in individual attention heads, inherent cross-modal alignment learned through contextualized multimodal embeddings). Through extensive analysis of each archetypal model architecture via these probing tasks, our key observations are: (i) Pre-trained models exhibit a propensity for attending over text rather than images during inference. (ii) There exists a subset of attention heads that are tailored for capturing cross-modal interactions. (iii) Learned attention matrix in pre-trained models demonstrates patterns coherent with the latent alignment between image regions and textual words. (iv) Plotted attention patterns reveal visually-interpretable relations among image regions. (v) Pure linguistic knowledge is also effectively encoded in the attention heads. These are valuable insights serving to guide future work towards designing better model architecture and objectives for multimodal pre-training."

Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting gradients from backpropagation to characterize data. Gradients capture model updates required to represent data. Anomalies require more drastic model updates to fully represent them compared to normal data. Hence, we propose the utilization of backpropagated gradients as representations to characterize model behavior on anomalies and, consequently, detect such anomalies. We show that the proposed method using gradient-based representations achieves state-of-the-art anomaly detection performance in benchmark image recognition datasets. Also, we highlight the computational efficiency and the simplicity of the proposed method in comparison with other state-of-the-art methods relying on adversarial networks or autoregressive models, which require at least 27 times more model parameters than the proposed method. "

Recent progress in fine-grained gesture and action classification, and machine translation, point to the possibility of automated sign language recognition becoming a reality. A key stumbling block in making progress towards this goal is a lack of appropriate training data, stemming from the high complexity of sign annotation and a limited supply of qualified annotators. In this work, we introduce a new scalable approach to data collection for sign recognition in continuous videos. We make use of weakly-aligned subtitles for broadcast footage together with a keyword spotting method to automatically localise sign-instances for a vocabulary of 1,000 signs in 1,000 hours of video. We make the following contributions: (1) We show how to use mouthing cues from signers to obtain high-quality annotations from video data - the result is the BSL-1K dataset, a collection of British Sign Language (BSL) signs of unprecedented scale; (2) We show that we can use BSL-1K to train strong sign recognition models for co-articulated signs in BSL and that these models additionally form excellent pretraining for other sign languages and benchmarks---we exceed the state of the art on both the MSASL and WLASL benchmarks. Finally, (3) we propose new large-scale evaluation sets for the tasks of sign recognition and sign spotting and provide baselines which we hope will serve to stimulate research in this area."

Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation. First, we develop the bilateral motion network with the bilateral cost volume to estimate bilateral motions accurately. Then, we approximate bi-directional motions to predict a different kind of bilateral motions. We then warp the two input frames using the estimated bilateral motions. Next, we develop the dynamic filter generation network to yield dynamic blending filters. Finally, we combine the warped frames using the dynamic blending filters to generate intermediate frames. Experimental results show that the proposed algorithm outperforms the state-of-the-art video interpolation algorithms on several benchmark datasets."

We introduce BLSM, a bone-level skinned model of the human body mesh where bone scales are set prior to template synthesis, rather than the common, inverse practice. BLSM first sets bone lengths and joint angles to specify the skeleton, then specifies identity-specific surface variation, and finally bundles them together through linear blend skinning. We design these steps by constraining the joint angles to respect the kinematic constraints of the human body and by using accurate mesh convolution-based networks to capture identity-specific surface variation. We provide quantitative results on the problem of reconstructing a collection of 3D human scans, and show that we obtain improvements in reconstruction accuracy when comparing to a SMPL-type baseline. Our decoupled bone and shape representation also allows for out-of-box integration with standard graphics packages like Unity, facilitating full-body AR effects and image-driven character animation. Additional results and demos are available from the project webpage: http://arielai.com/blsm"

We consider the problem of video snapshot compressive imaging (SCI), where multiple high-speed frames are coded by different masks and then summed to a single measurement. This measurement and the modulation masks are fed into our Recurrent Neural Network (RNN) to reconstruct the desired high-speed frames. Our end-to-end sampling and reconstruction system is dubbed BIdirectional Recurrent Neural networks with Adversarial Training (BIRNAT). To our best knowledge, this is the first time that recurrent networks are employed to SCI problem. Our proposed BIRNAT outperforms other deep learning based algorithms and the state-of-the-art optimization based algorithm, DeSCI, through exploiting the underlying correlation of sequential video frames. BIRNAT employs a deep convolutional neural network with Resblock and feature map self-attention (AttRes-CNN) to reconstruct the first frame, based on which bidirectional RNN (Bi-RNN) is utilized to reconstruct the following frames in a sequential manner. To improve the quality of the reconstructed video, BIRNAT is further equipped with the adversarial training besides the mean square error loss. Extensive results on both simulation and real data (from two SCI cameras) demonstrate the superior performance of our BIRNAT system."

In this paper, we consider the problem to automatically reconstruct garment and body shapes from a single near-front view RGB image. To this end, we propose a layered garment representation on top of SMPL and novelly make the skinning weight of garment independent of the body mesh, which significantly improves the expression ability of our garment model. Compared with existing methods, our method can support more garment categories and recover more accurate geometry. To train our model, we construct two large scale datasets with ground truth body and garment geometries as well as paired color images. Compared with single mesh or non-parametric representation, our method can achieve more flexible control with separate meshes, makes applications like re-pose, garment transfer, and garment texture mapping possible."

Multi-level feature fusion is a fundamental topic in computer vision for detecting, segmenting, and classifying objects at various scales. When multi-level features meet multi-modal cues, the optimal fusion problem becomes a hot potato. In this paper, we make the first attempt to leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to develop a novel cascaded refinement network. In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views. This fuses RGB and depth modalities in a complementary way. Our simple yet efficient architecture, dubbed Bifurcated Backbone Strategy Network (BBS-Net), is backbone independent, and outperforms 18 SOTAs on seven challenging datasets using four metrics."

This paper proposes Binary ArchitecTure Search (BATS), a framework that drastically reduces the accuracy gap between binary neural networks and their real-valued counterparts by means of Neural Architecture Search (NAS). We show that directly applying NAS to the binary domain provides very poor results. To alleviate this, we describe, to our knowledge, for the first time, the 3 key ingredients for successfully applying NAS to the binary domain. Specifically, we (1) introduce and design a novel binary-oriented search space, (2) propose a new mechanism for controlling and stabilising the resulting searched topologies, (3) propose and validate a series of new search strategies for binary networks that lead to faster convergence and lower search times. Experimental results demonstrate the effectiveness of the proposed approach and the necessity of searching in the binary space directly. Moreover, (4) we set a new state-of-the-art for binary neural networks on CIFAR10, CIFAR100 and ImageNet datasets. Code will be made available."

Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a fully attentional network by restricting the attention to a local region. In this paper, we attempt to remove this constraint by factorizing 2D self-attention into two 1D self-attentions. This reduces computation complexity and allows performing attention within a larger or even global region. In companion, we also propose a position-sensitive self-attention design. Combining both yields our position-sensitive axial-attention layer, a novel building block that one could stack to form axial-attention models for image classification and dense prediction. We demonstrate the effectiveness of our model on four large-scale datasets. In particular, our model outperforms all existing stand-alone self-attention models on ImageNet. Our Axial-DeepLab improves 2.8% PQ over bottom-up state-of-the-art on COCO test-dev. This previous state-of-the-art is attained by our small variant that is 3.8x parameter-efficient and 27x computation-efficient. Axial-DeepLab also achieves state-of-the-art results on Mapillary Vistas and Cityscapes."

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models, that predict the current pixel from past pixels in a raster-scan ordering created with masked convolutions, we propose different autoregressive orderings over the inputs using various forms of masked convolutions to construct different views of the data. For a given input, the model produces a pair of predictions with two valid orderings, and is then trained to maximize the mutual information between the two outputs. These outputs can either be low-dimensional features for representation learning or output clusters corresponding to semantic labels for clustering. While masked convolutions are used during training, in inference, no masking is applied and we fall back to the standard convolution where the model has access to the full input. The proposed method outperforms the current state-of-the-art on unsupervised image segmentation. It is simple and easy to implement, and can be extended to other visual tasks and integrated seamlessly into existing unsupervised learning methods requiring different views of the data."

We consider graph-based semi-supervised learning that leverages a similarity graph across data points to better exploit data structure exposed in unlabeled data. One challenge that arises in this problem context is that conventional matrix completion which can serve to construct a similarity graph entails heavy computational overhead, since it re-trains the graph independently whenever model parameters of an interested classifier are updated. In this paper, we propose a holistic approach that employs a parameterized neural-net-based autoencoder for matrix completion, thereby enabling simultaneous training between models of the classifier and matrix completion. We find that this approach not only speeds up training time (around a three-fold improvement over a prior approach), but also offers a higher prediction accuracy via a more accurate graph estimate. We demonstrate that our algorithm obtains state-of-the-art performances by respectful margins on benchmark datasets: Achieving the error rates of 0.57\% on MNIST with 100 labels; 3.48\% on SVHN with 1000 labels; and 6.87\% on CIFAR-10 with 4000 labels."

Current methods for trajectory prediction operate in supervised manners, and therefore require vast quantities of corresponding ground truth data for training. In this paper, we present a novel, label-free algorithm, AutoTrajectory, for trajectory extraction and prediction to use raw videos directly. To better capture the moving objects in videos, we introduce dynamic points. We use them to model dynamic motions by using a forward-backward extractor to keep temporal consistency and using image reconstruction to keep spatial consistency in an unsupervised manner. Then we aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos. Finally, we extract trajectories by matching instance points for prediction training. To the best of our knowledge, our method is the first to achieve unsupervised learning of trajectory extraction and prediction. We evaluate the performance on well-known trajectory datasets and show that our method is effective for real-world videos and can use raw videos to further improve the performance of existing models."

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually relying on REINFORCE-like gradient estimators. However these approaches are very expensive as they treat the entire data generation, model training, and validation pipeline as a black-box and require multiple costly objective evaluations at each iteration. We propose an efficient alternative for optimal synthetic data generation, based on a novel differentiable approximation of the objective. This allows us to optimize the simulator, which may be non-differentiable, requiring only one objective evaluation at each iteration with a little overhead. We demonstrate on a state-of-the-art photorealistic renderer that the proposed method finds the optimal data distribution faster (up to 50 times), with significantly reduced training data generation and better accuracy than previous methods."

Scene text recognition (STR) is challenging due to the diversity of text instances and the complexity of scenes. However, no STR methods can adapt backbones to different diversities and complexities. In this work, inspired by the success of neural architecture search (NAS), we propose automated STR (AutoSTR), which can address the above issue by searching data-dependent backbones. Specifically, we show both choices on operations and the downsampling path are very important in the search space design of NAS. Besides, since no existing NAS algorithms can handle the spatial constraint on the path, we propose a two-step search algorithm, which decouples operations and downsampling path, for an efficient search in the given space. Experiments demonstrate that, by searching data-dependent backbones, AutoSTR can outperform the state-of-the-art approaches on standard benchmarks with much fewer FLOPS and model parameters."