Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00960
Mingyuan Liu, D. Schonfeld, Wei Tang
Dependency relations among visual entities are ubiquity because both objects and scenes are highly structured. They provide prior knowledge about the real world that can help improve the generalization ability of deep learning approaches. Different from contextual reasoning which focuses on feature aggregation in the spatial domain, visual dependency reasoning explicitly models the dependency relations among visual entities. In this paper, we introduce a novel network architecture, termed the dependency network or DependencyNet, for semantic segmentation. It unifies dependency reasoning at three semantic levels. Intra-class reasoning decouples the representations of different object categories and updates them separately based on the internal object structures. Inter-class reasoning then performs spatial and semantic reasoning based on the dependency relations among different object categories. We will have an in-depth investigation on how to discover the dependency graph from the training annotations. Global dependency reasoning further refines the representations of each object category based on the global scene information. Extensive ablative studies with a controlled model size and the same network depth show that each individual dependency reasoning component benefits semantic segmentation and they together significantly improve the base network. Experimental results on two benchmark datasets show the DependencyNet achieves comparable performance to the recent states of the art.
{"title":"Exploit Visual Dependency Relations for Semantic Segmentation","authors":"Mingyuan Liu, D. Schonfeld, Wei Tang","doi":"10.1109/CVPR46437.2021.00960","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00960","url":null,"abstract":"Dependency relations among visual entities are ubiquity because both objects and scenes are highly structured. They provide prior knowledge about the real world that can help improve the generalization ability of deep learning approaches. Different from contextual reasoning which focuses on feature aggregation in the spatial domain, visual dependency reasoning explicitly models the dependency relations among visual entities. In this paper, we introduce a novel network architecture, termed the dependency network or DependencyNet, for semantic segmentation. It unifies dependency reasoning at three semantic levels. Intra-class reasoning decouples the representations of different object categories and updates them separately based on the internal object structures. Inter-class reasoning then performs spatial and semantic reasoning based on the dependency relations among different object categories. We will have an in-depth investigation on how to discover the dependency graph from the training annotations. Global dependency reasoning further refines the representations of each object category based on the global scene information. Extensive ablative studies with a controlled model size and the same network depth show that each individual dependency reasoning component benefits semantic segmentation and they together significantly improve the base network. Experimental results on two benchmark datasets show the DependencyNet achieves comparable performance to the recent states of the art.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123719226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01126
Andreas Meuleman, Hyeonjoong Jang, D. S. Jeon, Min H. Kim
A set of cameras with fisheye lenses have been used to capture a wide field of view. The traditional scan-line stereo algorithms based on epipolar geometry are directly inapplicable to this non-pinhole camera setup due to optical characteristics of fisheye lenses; hence, existing complete 360° RGB-D imaging systems have rarely achieved realtime performance yet. In this paper, we introduce an efficient sphere-sweeping stereo that can run directly on multiview fisheye images without requiring additional spherical rectification. Our main contributions are: First, we introduce an adaptive spherical matching method that accounts for each input fisheye camera’s resolving power concerning spherical distortion. Second, we propose a fast inter-scale bilateral cost volume filtering method that refines distance in noisy and textureless regions with optimal complexity of O(n). It enables real-time dense distance estimation while preserving edges. Lastly, the fisheye color and distance images are seamlessly combined into a complete 360° RGB-D image via fast inpainting of the dense distance map. We demonstrate an embedded 360° RGB-D imaging prototype composed of a mobile GPU and four fisheye cameras. Our prototype is capable of capturing complete 360° RGB-D videos with a resolution of two megapixels at 29 fps. Results demonstrate that our real-time method outperforms traditional omnidirectional stereo and learning-based omnidirectional stereo in terms of accuracy and performance.
{"title":"Real-Time Sphere Sweeping Stereo from Multiview Fisheye Images","authors":"Andreas Meuleman, Hyeonjoong Jang, D. S. Jeon, Min H. Kim","doi":"10.1109/CVPR46437.2021.01126","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01126","url":null,"abstract":"A set of cameras with fisheye lenses have been used to capture a wide field of view. The traditional scan-line stereo algorithms based on epipolar geometry are directly inapplicable to this non-pinhole camera setup due to optical characteristics of fisheye lenses; hence, existing complete 360° RGB-D imaging systems have rarely achieved realtime performance yet. In this paper, we introduce an efficient sphere-sweeping stereo that can run directly on multiview fisheye images without requiring additional spherical rectification. Our main contributions are: First, we introduce an adaptive spherical matching method that accounts for each input fisheye camera’s resolving power concerning spherical distortion. Second, we propose a fast inter-scale bilateral cost volume filtering method that refines distance in noisy and textureless regions with optimal complexity of O(n). It enables real-time dense distance estimation while preserving edges. Lastly, the fisheye color and distance images are seamlessly combined into a complete 360° RGB-D image via fast inpainting of the dense distance map. We demonstrate an embedded 360° RGB-D imaging prototype composed of a mobile GPU and four fisheye cameras. Our prototype is capable of capturing complete 360° RGB-D videos with a resolution of two megapixels at 29 fps. Results demonstrate that our real-time method outperforms traditional omnidirectional stereo and learning-based omnidirectional stereo in terms of accuracy and performance.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123727539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00579
Qi Feng, Vitaly Ablavsky, Qinxun Bai, S. Sclaroff
We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL) descriptions task. The proposed SNLT is applicable to a wide range of Siamese trackers, providing a new class of baselines for the tracking by NL task and promising future improvements from the advancements of Siamese trackers. The carefully designed architecture of the Siamese Natural Language Region Proposal Network (SNL-RPN), together with the Dynamic Aggregation of vision and language modalities, is introduced to perform the tracking by NL task. Empirical results over tracking benchmarks with NL annotations show that the proposed SNLT improves Siamese trackers by 3 to 7 percentage points with a slight tradeoff of speed. The proposed SNLT outperforms all NL trackers to-date and is competitive among state-of-the-art real-time trackers on LaSOT benchmarks while running at 50 frames per second on a single GPU. Code for this work is available at https://github.com/fredfung007/snlt.
{"title":"Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers","authors":"Qi Feng, Vitaly Ablavsky, Qinxun Bai, S. Sclaroff","doi":"10.1109/CVPR46437.2021.00579","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00579","url":null,"abstract":"We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL) descriptions task. The proposed SNLT is applicable to a wide range of Siamese trackers, providing a new class of baselines for the tracking by NL task and promising future improvements from the advancements of Siamese trackers. The carefully designed architecture of the Siamese Natural Language Region Proposal Network (SNL-RPN), together with the Dynamic Aggregation of vision and language modalities, is introduced to perform the tracking by NL task. Empirical results over tracking benchmarks with NL annotations show that the proposed SNLT improves Siamese trackers by 3 to 7 percentage points with a slight tradeoff of speed. The proposed SNLT outperforms all NL trackers to-date and is competitive among state-of-the-art real-time trackers on LaSOT benchmarks while running at 50 frames per second on a single GPU. Code for this work is available at https://github.com/fredfung007/snlt.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132857029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01297
A. Poulenard, L. Guibas
Learning pose invariant representation is a fundamental problem in shape analysis. Most existing deep learning algorithms for 3D shape analysis are not robust to rotations and are often trained on synthetic datasets consisting of pre-aligned shapes, yielding poor generalization to unseen poses. This observation motivates a growing interest in rotation invariant and equivariant methods. The field of rotation equivariant deep learning is developing in recent years thanks to a well established theory of Lie group representations and convolutions. A fundamental problem in equivariant deep learning is to design activation functions which are both informative and preserve equivariance. The recently introduced Tensor Field Network (TFN) framework provides a rotation equivariant network design for point cloud analysis. TFN features undergo a rotation in feature space given a rotation of the input pointcloud. TFN and similar designs consider nonlinearities which operate only over rotation invariant features such as the norm of equivariant features to preserve equivariance, making them unable to capture the directional information. In a recent work entitled "Gauge Equivariant Mesh CNNs: Anisotropic Convolutions on Geometric Graphs" Hann et al. interpret 2D rotation equivariant features as Fourier coefficients of functions on the circle. In this work we transpose the idea of Hann et al. to 3D by interpreting TFN features as spherical harmonics coefficients of functions on the sphere. We introduce a new equivariant nonlinearity and pooling for TFN. We show improvments over the original TFN design and other equivariant nonlinearities in classification and segmentation tasks. Furthermore our method is competitive with state of the art rotation invariant methods in some instances.
{"title":"A functional approach to rotation equivariant non-linearities for Tensor Field Networks","authors":"A. Poulenard, L. Guibas","doi":"10.1109/CVPR46437.2021.01297","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01297","url":null,"abstract":"Learning pose invariant representation is a fundamental problem in shape analysis. Most existing deep learning algorithms for 3D shape analysis are not robust to rotations and are often trained on synthetic datasets consisting of pre-aligned shapes, yielding poor generalization to unseen poses. This observation motivates a growing interest in rotation invariant and equivariant methods. The field of rotation equivariant deep learning is developing in recent years thanks to a well established theory of Lie group representations and convolutions. A fundamental problem in equivariant deep learning is to design activation functions which are both informative and preserve equivariance. The recently introduced Tensor Field Network (TFN) framework provides a rotation equivariant network design for point cloud analysis. TFN features undergo a rotation in feature space given a rotation of the input pointcloud. TFN and similar designs consider nonlinearities which operate only over rotation invariant features such as the norm of equivariant features to preserve equivariance, making them unable to capture the directional information. In a recent work entitled \"Gauge Equivariant Mesh CNNs: Anisotropic Convolutions on Geometric Graphs\" Hann et al. interpret 2D rotation equivariant features as Fourier coefficients of functions on the circle. In this work we transpose the idea of Hann et al. to 3D by interpreting TFN features as spherical harmonics coefficients of functions on the sphere. We introduce a new equivariant nonlinearity and pooling for TFN. We show improvments over the original TFN design and other equivariant nonlinearities in classification and segmentation tasks. Furthermore our method is competitive with state of the art rotation invariant methods in some instances.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132261143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00207
Junyong Lee, Hyeongseok Son, Jaesung Rim, Sunghyun Cho, Seungyong Lee
We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) that is specifically designed to handle spatially-varying and large defocus blur. For adaptively handling spatially-varying blur, IFAN predicts pixel-wise deblurring filters, which are applied to defocused features of an input image to generate deblurred features. For effectively managing large blur, IFAN models deblurring filters as stacks of small-sized separable filters. Predicted separable deblurring filters are applied to defocused features using a novel Iterative Adaptive Convolution (IAC) layer. We also propose a training scheme based on defocus disparity estimation and reblurring, which significantly boosts the de-blurring quality. We demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively on real-world images.
{"title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","authors":"Junyong Lee, Hyeongseok Son, Jaesung Rim, Sunghyun Cho, Seungyong Lee","doi":"10.1109/CVPR46437.2021.00207","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00207","url":null,"abstract":"We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) that is specifically designed to handle spatially-varying and large defocus blur. For adaptively handling spatially-varying blur, IFAN predicts pixel-wise deblurring filters, which are applied to defocused features of an input image to generate deblurred features. For effectively managing large blur, IFAN models deblurring filters as stacks of small-sized separable filters. Predicted separable deblurring filters are applied to defocused features using a novel Iterative Adaptive Convolution (IAC) layer. We also propose a training scheme based on defocus disparity estimation and reblurring, which significantly boosts the de-blurring quality. We demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively on real-world images.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132300950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00921
Mariem Mezghanni, Malika Boulkenafed, A. Lieutier, M. Ovsjanikov
Shapes are often designed to satisfy structural properties and serve a particular functionality in the physical world. Unfortunately, most existing generative models focus primarily on the geometric or visual plausibility, ignoring the physical or structural constraints. To remedy this, we present a novel method aimed to endow deep generative models with physical reasoning. In particular, we introduce a loss and a learning framework that promote two key characteristics of the generated shapes: their connectivity and physical stability. The former ensures that each generated shape consists of a single connected component, while the latter promotes the stability of that shape when subjected to gravity. Our proposed physical losses are fully differentiable and we demonstrate their use in end-to-end learning. Crucially we demonstrate that such physical objectives can be achieved without sacrificing the expressive power of the model and variability of the generated results. We demonstrate through extensive comparisons with the state-of-the-art deep generative models, the utility and efficiency of our proposed approach, while avoiding the potentially costly differentiable physical simulation at training time.
{"title":"Physically-aware Generative Network for 3D Shape Modeling","authors":"Mariem Mezghanni, Malika Boulkenafed, A. Lieutier, M. Ovsjanikov","doi":"10.1109/CVPR46437.2021.00921","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00921","url":null,"abstract":"Shapes are often designed to satisfy structural properties and serve a particular functionality in the physical world. Unfortunately, most existing generative models focus primarily on the geometric or visual plausibility, ignoring the physical or structural constraints. To remedy this, we present a novel method aimed to endow deep generative models with physical reasoning. In particular, we introduce a loss and a learning framework that promote two key characteristics of the generated shapes: their connectivity and physical stability. The former ensures that each generated shape consists of a single connected component, while the latter promotes the stability of that shape when subjected to gravity. Our proposed physical losses are fully differentiable and we demonstrate their use in end-to-end learning. Crucially we demonstrate that such physical objectives can be achieved without sacrificing the expressive power of the model and variability of the generated results. We demonstrate through extensive comparisons with the state-of-the-art deep generative models, the utility and efficiency of our proposed approach, while avoiding the potentially costly differentiable physical simulation at training time.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130420997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01510
Phi Vu Tran
Recent years have seen flourishing research on both semi-supervised learning and 3D room layout reconstruction. In this work, we explore the intersection of these two fields to advance the research objective of enabling more accurate 3D indoor scene modeling with less labeled data. We propose the first approach to learn representations of room corners and boundaries by using a combination of labeled and unlabeled data for improved layout estimation in a 360° panoramic scene. Through extensive comparative experiments, we demonstrate that our approach can advance layout estimation of complex indoor scenes using as few as 20 labeled examples. When coupled with a layout predictor pre-trained on synthetic data, our semi-supervised method matches the fully supervised counterpart using only 12% of the labels. Our work takes an important first step towards robust semi-supervised layout estimation that can enable many applications in 3D perception with limited labeled data.
{"title":"SSLayout360: Semi-Supervised Indoor Layout Estimation from 360° Panorama","authors":"Phi Vu Tran","doi":"10.1109/CVPR46437.2021.01510","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01510","url":null,"abstract":"Recent years have seen flourishing research on both semi-supervised learning and 3D room layout reconstruction. In this work, we explore the intersection of these two fields to advance the research objective of enabling more accurate 3D indoor scene modeling with less labeled data. We propose the first approach to learn representations of room corners and boundaries by using a combination of labeled and unlabeled data for improved layout estimation in a 360° panoramic scene. Through extensive comparative experiments, we demonstrate that our approach can advance layout estimation of complex indoor scenes using as few as 20 labeled examples. When coupled with a layout predictor pre-trained on synthetic data, our semi-supervised method matches the fully supervised counterpart using only 12% of the labels. Our work takes an important first step towards robust semi-supervised layout estimation that can enable many applications in 3D perception with limited labeled data.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130456444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00174
Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
Most existing video text detection methods track texts with appearance features, which are easily influenced by the change of perspective and illumination. Compared with appearance features, semantic features are more robust cues for matching text instances. In this paper, we propose an end-to-end trainable video text detector that tracks texts based on semantic features. First, we introduce a new character center segmentation branch to extract semantic features, which encode the category and position of characters. Then we propose a novel appearance-semantic-geometry descriptor to track text instances, in which se-mantic features can improve the robustness against appearance changes. To overcome the lack of character-level an-notations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels. The proposed method achieves state-of-the-art performance on three video text benchmarks ICDAR 2013 Video, Minetto and RT-1K, and two Chinese scene text benchmarks CA-SIA10K and MSRA-TD500.
{"title":"Semantic-Aware Video Text Detection","authors":"Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu","doi":"10.1109/CVPR46437.2021.00174","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00174","url":null,"abstract":"Most existing video text detection methods track texts with appearance features, which are easily influenced by the change of perspective and illumination. Compared with appearance features, semantic features are more robust cues for matching text instances. In this paper, we propose an end-to-end trainable video text detector that tracks texts based on semantic features. First, we introduce a new character center segmentation branch to extract semantic features, which encode the category and position of characters. Then we propose a novel appearance-semantic-geometry descriptor to track text instances, in which se-mantic features can improve the robustness against appearance changes. To overcome the lack of character-level an-notations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels. The proposed method achieves state-of-the-art performance on three video text benchmarks ICDAR 2013 Video, Minetto and RT-1K, and two Chinese scene text benchmarks CA-SIA10K and MSRA-TD500.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127992217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00686
Wenda Zhao, Cai Shang, Huchuan Lu
Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highly time-consuming and error-prone. Addressing this issue, this paper makes an effort to train a deep DBD model without using any pixel-level annotation. The core insight is that a defocus blur region/focused clear area can be arbitrarily pasted to a given realistic full blurred image/full clear image without affecting the judgment of the full blurred image/full clear image. Specifically, we train a generator G in an adversarial manner against dual discriminators Dc and Db. G learns to produce a DBD mask that generates a composite clear image and a composite blurred image through copying the focused area and unfocused region from corresponding source image to another full clear image and full blurred image. Then, Dc and Db can not distinguish them from realistic full clear image and full blurred image simultaneously, achieving a self-generated DBD by an implicit manner to define what a defocus blur area is. Besides, we propose a bilateral triplet-excavating constraint to avoid the degenerate problem caused by the case one discriminator defeats the other one. Comprehensive experiments on two widely-used DBD datasets demonstrate the superiority of the proposed approach. Source codes are available at: https://github.com/shangcai1/SG.
{"title":"Self-generated Defocus Blur Detection via Dual Adversarial Discriminators","authors":"Wenda Zhao, Cai Shang, Huchuan Lu","doi":"10.1109/CVPR46437.2021.00686","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00686","url":null,"abstract":"Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highly time-consuming and error-prone. Addressing this issue, this paper makes an effort to train a deep DBD model without using any pixel-level annotation. The core insight is that a defocus blur region/focused clear area can be arbitrarily pasted to a given realistic full blurred image/full clear image without affecting the judgment of the full blurred image/full clear image. Specifically, we train a generator G in an adversarial manner against dual discriminators Dc and Db. G learns to produce a DBD mask that generates a composite clear image and a composite blurred image through copying the focused area and unfocused region from corresponding source image to another full clear image and full blurred image. Then, Dc and Db can not distinguish them from realistic full clear image and full blurred image simultaneously, achieving a self-generated DBD by an implicit manner to define what a defocus blur area is. Besides, we propose a bilateral triplet-excavating constraint to avoid the degenerate problem caused by the case one discriminator defeats the other one. Comprehensive experiments on two widely-used DBD datasets demonstrate the superiority of the proposed approach. Source codes are available at: https://github.com/shangcai1/SG.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128829362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01256
Yasamin Jafarian, H. Park
A key challenge of learning the geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D human reconstruction when applying to real-world imagery. We address this challenge by leveraging a new data resource: a number of social media dance videos that span diverse appearance, clothing styles, performances, and identities. Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry. To utilize these videos, we present a new method to use the local transformation that warps the predicted local geometry of the person from an image to that of another image at a different time instant. This allows self-supervision as enforcing a temporal coherence over the predictions. In addition, we jointly learn the depth along with the surface normals that are highly responsive to local texture, wrinkle, and shade by maximizing their geometric consistency. Our method is end-to-end trainable, resulting in high fidelity depth estimation that predicts fine geometry faithful to the input real image. We demonstrate that our method outperforms the state-of-the-art human depth estimation and human shape recovery approaches on both real and rendered images.
{"title":"Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos","authors":"Yasamin Jafarian, H. Park","doi":"10.1109/CVPR46437.2021.01256","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01256","url":null,"abstract":"A key challenge of learning the geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D human reconstruction when applying to real-world imagery. We address this challenge by leveraging a new data resource: a number of social media dance videos that span diverse appearance, clothing styles, performances, and identities. Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry. To utilize these videos, we present a new method to use the local transformation that warps the predicted local geometry of the person from an image to that of another image at a different time instant. This allows self-supervision as enforcing a temporal coherence over the predictions. In addition, we jointly learn the depth along with the surface normals that are highly responsive to local texture, wrinkle, and shade by maximizing their geometric consistency. Our method is end-to-end trainable, resulting in high fidelity depth estimation that predicts fine geometry faithful to the input real image. We demonstrate that our method outperforms the state-of-the-art human depth estimation and human shape recovery approaches on both real and rendered images.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123092805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：