In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem.
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
Advances in low-light video RAW-to-RGB translation are opening up the possibility of fast low-light imaging on commodity devices (e.g. smartphone cameras) without the need for a tripod. However,it is challenging to collect the required paired short-long exposure frames to learn a supervised mapping. Current approaches require a specialised rig or the use of static videos with no subject or object motion [5],resulting in datasets that are limited in size, diversity, and motion. We address the data collection bottleneck for low-light video RAW-to-RGB by proposing a data synthesis mechanism, dubbed SIDGAN, that can generate abundant dynamic video training pairs. SIDGAN maps videos found ‘in the wild’ (e.g. internet videos) into a low-light (short, long exposure) domain. By generating dynamic video data synthetically, we enable a recently proposed state-of-the-art RAW-to-RGB model to attain higher image quality (improved colour, reduced artifacts) and improved temporal consistency, compared to the same model trained with only static real video data
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoireing. Existing image restoration methods working in the RGB domain have difficulty in distinguishing moire patterns from true scene texture. Unlike these methods,our network removes moire patterns in the wavelet domain to separate the frequencies of moire patterns from the image content. The network combines dense convolution modules and dilated convolution modules supporting large receptive fields. Extensive experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moire artifacts on non-screen images. Although designed for image demoireing, WDNet has been applied to two other low-level vision tasks, outperforming state-of-the-art image deraining and derain-drop methods on the Rain100h and Raindrop800 data sets, respectively.
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks. In this paper, we defend against adversarial attacks using neural architecture search (NAS) which is based on a comprehensive search of denoising blocks, weight-free operations, Gabor filters and convolutions. The resulting anti-bandit NAS (ABanditNAS) incorporates a new operation evaluation measure and search process based on the lower and upper confidence bounds (LCB and UCB). Unlike the conventional bandit algorithm using UCB for evaluation only, we use UCB to abandon arms for search efficiency and LCB for a fair competition between arms. Extensive experiments demonstrate that ABanditNAS is about twice as fast as the state-of-the-art NAS method, while achieving an $8.73\%$ improvement over prior arts on CIFAR-10 under PGD-$7$.
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data, but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.
We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D pose representation. This is realized by learning a generative pose embedding which not only ensures plausible 3D pose predictions, but also eliminates the usual keypoint grouping operation as employed in prior bottom-up approaches. Further, we propose a practical deployment paradigm where paired 2D or 3D pose annotations are unavailable. In the absence of any paired supervision, we leverage a frozen network, as a teacher model, which is trained on an auxiliary task of multi-person 2D pose estimation. We cast the learning as a cross-modal alignment problem and propose training objectives to realize a shared latent space between two diverse modalities. We aim to enhance the model's ability to perform beyond the limiting teacher network by enriching the latent-to-3D pose mapping using artificially synthesized multi-person 3D scene samples. Our approach not only generalizes to in-the-wild images, but also yields a superior trade-off between speed and performance, compared to prior top-down approaches. Our approach also yields state-of-the-art multi-person 3D pose estimation performance among the bottom-up approaches under consistent supervision levels.
Recent studies have shown that current VQA models are heavily biased on the language priors in the train set to answer the question, irrespective of the image. E.g., overwhelmingly answer ""what sport is"" as ""tennis"" or ""what color banana"" as ""yellow."" This behavior restricts them from real-world application scenarios. In this work, we propose a novel model-agnostic question encoder, Visually-Grounded Question Encoder (VGQE), for VQA that reduces this effect. VGQE utilizes both visual and language modalities equally while encoding the question. Hence the question representation itself gets sufficient visual-grounding, and thus reduces the dependency of the model on the language priors. We demonstrate the effect of VGQE on three recent VQA models and achieve state-of-the-art results on the bias-sensitive split of the VQAv2 dataset; VQA-CPv2. Further, unlike the existing bias-reduction techniques, on the standard VQAv2 benchmark, our approach does not drop the accuracy; instead, it improves the performance.
Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides the need of correctly presenting the attributes of items, the expressions in an enchanting style could better attract customer interests. The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning. Different from popular work on image captioning, it is hard to identify and describe the rich attributes of fashion items. We seed the description of an item by first identifying its attributes, and introduce attribute-level semantic (ALS) reward and sentence-level semantic (SLS) reward as metrics to improve the quality of text descriptions. We further integrate the training of our model with maximum likelihood estimation (MLE), attribute embedding, and Reinforcement Learning (RL). To facilitate the learning, we build a new FAshion CAptioning Dataset (FACAD), which contains 800K images and 120K corresponding enchanting and diverse descriptions. Experiments on FACAD demonstrate the effectiveness of our model.
Recent studies on facial expression editing have obtained very promising progress. On the other hand, existing methods face the constraint of requiring a large amount of expression labels which are often expensive and time-consuming to collect. This paper presents an innovative label-free expression editing via disentanglement (LEED) framework that is capable of editing the expression of both frontal and profile facial images without requiring any expression labels. The idea is to disentangle the identity and expression of a facial image in the expression manifold, where the neutral face captures the identity attribute and the displacement between the neutral image and the expressive image captures the expression attribute. Two novel losses are designed for optimal expression disentanglement and consistent synthesis, including a mutual expression information loss that aims to extract pure expression-related features and a siamese loss that aims to enhance the expression similarity between the synthesized image and the reference image. Extensive experiments over two public facial expression datasets show that LEED achieves superior facial expression editing qualitatively and quantitatively.
Representing a space of handwriting stroke styles includes the challenge of representing both the style of each character and the overall style of the human writer. Existing VRNN approaches to representing handwriting often do not distinguish between these different style components, which can reduce model capability. Instead, we introduce the Decoupled Style Descriptor (DSD) model for handwriting, which factors both character- and writer-level styles and allows our model to represent an overall greater space of styles. This approach also increases flexibility: given a few examples, we can generate handwriting in new writer styles, and also now generate handwriting of new characters across writer styles. In experiments, our generated results were preferred over a state of the art baseline method 88% of the time, and in a writer identification task on 20 held-out writers, our DSDs achieved 89.38% accuracy from a single sample word. Overall, DSDs allows us to improve both the quality and flexibility over existing handwriting stroke generation approaches.
Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data from test users which may not be attainable in real applications. We observe that there exists a strong relationship between what users are looking at and the appearance of the user’s eyes. In response to this understanding, we propose a novel dataset and accompanying method which aims to explicitly learn these semantic and temporal relationships. Our video dataset consists of time-synchronized screen recordings, user-facing camera views, and eye gaze data, which allows for new benchmarks in temporal gaze tracking as well as label-free refinement of gaze. Importantly, we demonstrate that the fusion of information from visual stimuli as well as eye images can lead towards achieving performance similar to literature-reported figures acquired through supervised personalization. Our final method yields significant performance improvements on our proposed EVE dataset, with up to 28% improvement in Point-of-Gaze estimates (resulting in 2.49-deg in angular error), paving the path towards high-accuracy screen-based eye tracking purely from webcam sensors. The dataset and reference source code are available at https://ait.ethz.ch/projects/2020/EVE
End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery
PDF ↗The automated segmentation of buildings in remote sensing imagery is a challenging task that requires the accurate delineation of multiple building instances over typically large image areas. Manual methods are often laborious and current deep-learning-based approaches fail to delineate all building instances and do so with adequate accuracy. As a solution, we present Trainable Deep Active Contours (TDACs), an automatic image segmentation framework that intimately unites Convolutional Neural Networks (CNNs) and Active Contour Models (ACMs). The Eulerian energy functional of the ACM component includes per-pixel parameter maps that are predicted by the backbone CNN, which also initializes the ACM. Importantly, both the ACM and CNN components are fully implemented in TensorFlow and the entire TDAC architecture is end-to-end automatically differentiable and backpropagation trainable without user intervention. TDAC yields fast, accurate, and fully automatic simultaneous delineation of arbitrarily many buildings in the image. We validate the model on two publicly available aerial image datasets for building segmentation, and our results demonstrate that TDAC establishes a new state-of-the-art performance.
We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide piecewise-smooth flow completion with sharp edges. Existing methods propagate colors among local flow connections between adjacent frames. However, not all missing regions in a video can be reached in this way because the motion boundaries form impenetrable barriers. Our method alleviates this problem by introducing non-local flow connections to temporally distant frames, enabling propagating video content over motion boundaries. We validate our approach on the DAVIS dataset. Both visual and quantitative results show that our method compares favorably against the state-of-the-art algorithms.
We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph (one human-centric and one object-centric). Our proposed dual relation graph effectively captures discriminative cues from the scene to resolve ambiguity from local predictions. Our model is conceptually simple and leads to favorable results when compared to the state-of-the-art HOI detection algorithms on two large-scale benchmark datasets.
We address the problem of domain adaptation in videos for the task of human action recognition. Inspired by image-based domain adaptation, we can perform video adaptation by aligning the features of frames or clips of source and target videos. However, equally aligning all clips is sub-optimal as not all clips are informative for the task. As the first novelty, we propose an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level (cf. clip-level) alignment. As the backgrounds are often very different between source and target, the source background-corrupted model adapts poorly to target domain videos. To alleviate this, as a second novelty, we propose to use the clip order prediction as an auxiliary task. The clip order prediction loss, when combined with domain adversarial loss, encourages learning of representations which focus on the humans and objects involved in the actions, rather than the uninformative and widely differing (between source and target) backgrounds. We empirically show that both components contribute positively towards adaptation performance. We report state-of-the-art performances on two out of three challenging public benchmarks, two based on the UCF and HMDB datasets, and one on Kinetics to NEC-Drone datasets. We also support the intuitions and the results with qualitative results.
We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have fixed and deterministic reshaping factors, our module allows for a learnable reshaping factor. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision, through which network architectures can be optimised for each individual task, in a fully automated way. We performed experiments across seven image classification datasets, and results show that by simply using a set of our shape adaptors instead of the original resizing layers, performance increases consistently over human-designed networks, across all datasets. Additionally, we show the effectiveness of shape adaptors on two other applications: network compression and transfer learning.
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame. It divides the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks. In addition, a hidden state adaptation module that allows the current frame to selectively use information from hidden state is introduced to enhance its robustness to appearance change and error accumulation. Extensive ablation study validate the effectiveness of the proposed modules. Experiments on several benchmark datasets demonstrate superior performance of the proposed method compared to state-of-the-art methods on video super-resolution.
We propose a new approach for combining deep-learned nonmetric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence. Considering the depth information and affine features, two new constraints on the camera pose are derived. The proposed solver is usable within 1-point RANSAC approaches. Thus, the processing time of the robust estimation is linear in the number of correspondences and, therefore, orders of magnitude faster than by using traditional approaches. The proposed 1AC+D solver is tested both on synthetic data and on 110 395 publicly available real image pairs where we used an off-the-shelf monocular depth network to provide up-to-scale depth per pixel. The proposed 1AC+D leads to similar accuracy as traditional approaches while being significantly faster. When solving large-scale problems, e.g. pose-graph initialization for Structure-from-Motion (SfM) pipelines, the overhead of obtaining ACs and monocular depth is negligible compared to the speed-up gained in the pairwise geometric verification, i.e., relative pose estimation. This is demonstrated on scenes from the 1DSfM dataset using a state-of-the-art global SfM algorithm.
This paper studies the problem of sparse residual regression, i.e., learning a linear model using a norm that favors solutions in which the residuals are sparsely distributed. This is a common problem in a wide range of computer vision applications where a linear system has a lot more equations than unknowns and we wish to find the maximum feasible set of equations by discarding unreliable ones. We show that one of the most popular solution methods, iteratively reweighted least squares (IRLS), can be significantly accelerated by the use of matrix sketching. We analyze the convergence behavior of the proposed method and show its efficiency on a range of computer vision applications.
We tackle a new problem of semantic view synthesis --- generating free-viewpoint rendering of a synthesized scene using a semantic label map as input. We build upon recent advances in semantic image synthesis and view synthesis for handling photographic image content generation and view extrapolation. Direct application of existing image/view synthesis methods, however, results in severe ghosting/blurry artifacts. To address the drawbacks, we propose a two-step approach. First, we focus on synthesizing the color and depth of the visible surface of the 3D scene. We then use the synthesized color and depth to impose explicit constraints on the multiple-plane image (MPI) representation prediction process. Our method produces sharp contents at the original view and geometrically consistent renderings across novel viewpoints. The experiments on numerous indoor and outdoor images show favorable results against several strong baselines and validate the effectiveness of our approach.