Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision最新文献_第2页

RRSR: Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection 基于互向参考的图像超分辨率渐进式特征对齐与选择

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-11-08 DOI: 10.48550/arXiv.2211.04203

Lin Zhang, Xin Li, Dongliang He, Fu Li, Yili Wang, Zhao Zhang

{"title":"RRSR: Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection","authors":"Lin Zhang, Xin Li, Dongliang He, Fu Li, Yili Wang, Zhao Zhang","doi":"10.48550/arXiv.2211.04203","DOIUrl":"https://doi.org/10.48550/arXiv.2211.04203","url":null,"abstract":"Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed SR image should enable better SR reconstruction for its similar LR images when it is referred to as. Therefore, in this work, we propose a reciprocal learning framework that can appropriately leverage such a fact to reinforce the learning of a RefSR network. Besides, we deliberately design a progressive feature alignment and selection module for further improving the RefSR task. The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection in a progressive manner, thus more precise reference features can be transferred into the input features and the network capability is enhanced. Our reciprocal learning paradigm is model-agnostic and it can be applied to arbitrary RefSR models. We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm. Furthermore, our proposed model together with the reciprocal learning strategy sets new state-of-the-art performances on multiple benchmarks.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89730799","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}

引用次数: 3

Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach 面向现实世界的HDRTV重建:一种基于数据综合的方法

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-11-06 DOI: 10.48550/arXiv.2211.03058

Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, C. Chen, Zhiwei Xiong

{"title":"Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach","authors":"Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, C. Chen, Zhiwei Xiong","doi":"10.48550/arXiv.2211.03058","DOIUrl":"https://doi.org/10.48550/arXiv.2211.03058","url":null,"abstract":"Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84938790","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}

引用次数: 5

Large Scale Real-World Multi-Person Tracking 大规模的真实世界多人跟踪

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-11-03 DOI: 10.48550/arXiv.2211.02175

Bing Shuai, Alessandro Bergamo, Uta Buechler, Andrew G. Berneshawi, Alyssa Boden, Joseph Tighe

{"title":"Large Scale Real-World Multi-Person Tracking","authors":"Bing Shuai, Alessandro Bergamo, Uta Buechler, Andrew G. Berneshawi, Alyssa Boden, Joseph Tighe","doi":"10.48550/arXiv.2211.02175","DOIUrl":"https://doi.org/10.48550/arXiv.2211.02175","url":null,"abstract":"This paper presents a new large scale multi-person tracking dataset -- texttt{PersonPath22}, which is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20 datasets. The lack of large scale training and test data for this task has limited the community's ability to understand the performance of their tracking systems on a wide range of scenarios and conditions such as variations in person density, actions being performed, weather, and time of day. texttt{PersonPath22} dataset was specifically sourced to provide a wide variety of these conditions and our annotations include rich meta-data such that the performance of a tracker can be evaluated along these different dimensions. The lack of training data has also limited the ability to perform end-to-end training of tracking systems. As such, the highest performing tracking systems all rely on strong detectors trained on external image datasets. We hope that the release of this dataset will enable new lines of research that take advantage of large scale video based training data.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73440223","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}

引用次数: 3

Bridging the Visual Semantic Gap in VLN via Semantically Richer Instructions 利用语义丰富的指令弥合VLN中的视觉语义差距

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-27 DOI: 10.1007/978-3-031-19836-6_4

Joaquín Ossandón, Benjamín Earle, Álvaro Soto

引用次数: 0

Addressing Heterogeneity in Federated Learning via Distributional Transformation 通过分布转换处理联邦学习中的异质性

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-26 DOI: 10.1007/978-3-031-19839-7_11

Haolin Yuan, Bo Hui, Yuchen Yang, P. Burlina, N. Gong, Yinzhi Cao

引用次数: 8

SUPR: A Sparse Unified Part-Based Human Representation SUPR:稀疏统一的基于部分的人类表征

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-25 DOI: 10.48550/arXiv.2210.13861

Ahmed A. A. Osman, Timo Bolkart, Dimitrios Tzionas, Michael J. Black

{"title":"SUPR: A Sparse Unified Part-Based Human Representation","authors":"Ahmed A. A. Osman, Timo Bolkart, Dimitrios Tzionas, Michael J. Black","doi":"10.48550/arXiv.2210.13861","DOIUrl":"https://doi.org/10.48550/arXiv.2210.13861","url":null,"abstract":"Statistical 3D shape models of the head, hands, and fullbody are widely used in computer vision and graphics. Despite their wide use, we show that existing models of the head and hands fail to capture the full range of motion for these parts. Moreover, existing work largely ignores the feet, which are crucial for modeling human movement and have applications in biomechanics, animation, and the footwear industry. The problem is that previous body part models are trained using 3D scans that are isolated to the individual parts. Such data does not capture the full range of motion for such parts, e.g. the motion of head relative to the neck. Our observation is that full-body scans provide important information about the motion of the body parts. Consequently, we propose a new learning scheme that jointly trains a full-body model and specific part models using a federated dataset of full-body and body-part scans. Specifically, we train an expressive human body model called SUPR (Sparse Unified Part-Based Human Representation), where each joint strictly influences a sparse set of model vertices. The factorized representation enables separating SUPR into an entire suite of body part models. Note that the feet have received little attention and existing 3D body models have highly under-actuated feet. Using novel 4D scans of feet, we train a model with an extended kinematic tree that captures the range of motion of the toes. Additionally, feet deform due to ground contact. To model this, we include a novel non-linear deformation function that predicts foot deformation conditioned on the foot pose, shape, and ground contact. We train SUPR on an unprecedented number of scans: 1.2 million body, head, hand and foot scans. We quantitatively compare SUPR and the separated body parts and find that our suite of models generalizes better than existing models. SUPR is available at http://supr.is.tue.mpg.de","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81404466","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}

引用次数: 13

Pointly-Supervised Panoptic Segmentation 点监督全视分割

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-25 DOI: 10.48550/arXiv.2210.13950

Junsong Fan, Zhaoxiang Zhang, T. Tan

引用次数: 10

Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement 基于逆运动学和改进的多人三维姿态和形状估计

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-24 DOI: 10.48550/arXiv.2210.13529

Junuk Cha, Muhammad Saqlain, Geonu Kim, Minjung Shin, Seungryul Baek

{"title":"Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement","authors":"Junuk Cha, Muhammad Saqlain, Geonu Kim, Minjung Shin, Seungryul Baek","doi":"10.48550/arXiv.2210.13529","DOIUrl":"https://doi.org/10.48550/arXiv.2210.13529","url":null,"abstract":"Estimating 3D poses and shapes in the form of meshes from monocular RGB images is challenging. Obviously, it is more difficult than estimating 3D poses only in the form of skeletons or heatmaps. When interacting persons are involved, the 3D mesh reconstruction becomes more challenging due to the ambiguity introduced by person-to-person occlusions. To tackle the challenges, we propose a coarse-to-fine pipeline that benefits from 1) inverse kinematics from the occlusion-robust 3D skeleton estimation and 2) Transformer-based relation-aware refinement techniques. In our pipeline, we first obtain occlusion-robust 3D skeletons for multiple persons from an RGB image. Then, we apply inverse kinematics to convert the estimated skeletons to deformable 3D mesh parameters. Finally, we apply the Transformer-based mesh refinement that refines the obtained mesh parameters considering intra- and inter-person relations of 3D meshes. Via extensive experiments, we demonstrate the effectiveness of our method, outperforming state-of-the-arts on 3DPW, MuPoTS and AGORA datasets.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84988368","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}

引用次数: 5

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval 基于不确定性学习的人图像检索可靠性感知预测

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-24 DOI: 10.1007/978-3-031-19781-9_34

Zhaopeng Dou, Zhongdao Wang, Weihua Chen, Yali Li, Shengjin Wang

引用次数: 4

SC-wLS: Towards Interpretable Feed-forward Camera Re-localization SC-wLS:面向可解释前馈摄像机的再定位

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-10-23 DOI: 10.1007/978-3-031-19769-7_34

Xin Wu, Hao Zhao, Shunkai Li, Yingdian Cao, H. Zha

引用次数: 7