3D 视觉 - arXivDaily 专题

2112.05498 2021-12-13 cs.CV 57%

Sparse Depth Completion with Semantic Mesh Deformation Optimization

Bing Zhou, Matias Aiskovich, Sinem Guven

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2112.04203 2021-12-09 cs.CV 57%

Adversarial Parametric Pose Prior

Andrey Davydov, Anastasia Remizova, Victor Constantin, Sina Honari, Mathieu Salzmann, Pascal Fua

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2112.04182 2021-12-09 cs.CV 57%

Unimodal Face Classification with Multimodal Training

Wenbin Teng, Chongyang Bai

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments Accepted by IEEE International Conference On Automatic Face and Gesture Recognition 2021

2104.14873 2021-12-02 eess.IV cs.CV 57%

Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas

Adrià Casamitjana, Marco Lorenzi, Sebastiano Ferraris, Loc Peter, Marc Modat, Allison Stevens, Bruce Fischl, Tom Vercauteren, Juan Eugenio Iglesias

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Medical Image Analysis (Accepted on 07/10/2021). 22 pages, 11 figures,

2011.12108 2021-12-02 cs.CV eess.IV 57%

Wide-angle Image Rectification: A Survey

Jinlong Fan, Jing Zhang, Stephen J. Maybank, Dacheng Tao

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted by the International Journal of Computer Vision (IJCV). Both the datasets and source code are available at https://github.com/loong8888/WAIR

2111.15404 2021-12-01 cs.CV 57%

Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model

Akash Sengupta, Ignas Budvytis, Roberto Cipolla

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments BMVC 2021

2111.15113 2021-12-01 cs.CV 57%

LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies

Sandro Lombardi, Bangbang Yang, Tianxing Fan, Hujun Bao, Guofeng Zhang, Marc Pollefeys, Zhaopeng Cui

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted to 3DV 2021. Project Page: https://latenthuman.github.io/

2111.13295 2021-12-01 cs.CV cs.AI 57%

Medial Spectral Coordinates for 3D Shape Analysis

Morteza Rezanejad, Mohammad Khodadad, Hamidreza Mahyar, Herve Lombaert, Michael Gruninger, Dirk B. Walther, Kaleem Siddiqi

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2111.03039 2021-12-01 cs.CV 57%

Towards Panoptic 3D Parsing for Single Image in the Wild

Sainan Liu, Vincent Nguyen, Yuan Gao, Subarna Tripathi, Zhuowen Tu

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2007.11432 2021-11-29 cs.CV 57%

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction

Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments Accepted at ECCV'20 (Oral)

2111.13023 2021-11-29 cs.CV cs.LG 57%

Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image

Joshua Mitton, Chaitanya Kaul, Roderick Murray-Smith

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2012.04718 2021-11-29 cs.CV cs.LG 57%

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments NeurIPS 2021; The first two authors contributed equally; Project website: https://canonical-capsules.github.io

2111.10371 2021-11-23 eess.IV cs.CV cs.LG 57%

ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction

Yubo Zhang, Jan-Michael Frahm, Samuel Ehrenstein, Sarah K. McGill, Julian G. Rosenman, Shuxian Wang, Stephen M. Pizer

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 13 pages, 5 figures

2001.09322 2021-11-23 cs.CV 57%

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

Dengsheng Chen, Jun Li, Zheng Wang, Kai Xu

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2111.06838 2021-11-15 cs.CV 57%

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

Jan Bednarik, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments 21 pages. arXiv admin note: substantial text overlap with arXiv:2104.06950

2111.02045 2021-11-04 cs.CV 57%

Deep Point Set Resampling via Gradient Fields

Haolan Chen, Bi'an Du, Shitong Luo, Wei Hu

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:2107.10981

2110.15267 2021-10-29 cs.CV 57%

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Haonan Yan, Jiaqi Chen, Xujie Zhang, Shengkai Zhang, Nianhong Jiao, Xiaodan Liang, Tianxiang Zheng

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted to ICCV 2021

Journal ref ICCV 2021

2110.14590 2021-10-28 cs.CV cs.AI cs.LG 57%

TMBuD: A dataset for urban scene building detection

Orhei Ciprian, Vert Silviu, Mocofan Muguras, Vasiu Radu

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2110.11601 2021-10-26 cs.CV 57%

Multimodal Semi-Supervised Learning for 3D Objects

Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian, Bing Li

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments BMVC 2021 poster

2108.08478 2021-10-26 cs.CV 57%

Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction

Fang Zhao, Wenhao Wang, Shengcai Liao, Ling Shao

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments ICCV 2021 (Oral). Code is available at https://github.com/zhaofang0627/AnchorUDF

2104.06703 2021-10-26 cs.CV cs.LG 57%

Deep Permutation Equivariant Structure from Motion

Dror Moran, Hodaya Koslowsky, Yoni Kasten, Haggai Maron, Meirav Galun, Ronen Basri

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2110.11036 2021-10-22 cs.CV 57%

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti, Luigi Di Stefano

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments 3DV 2021 (Oral) Code: https://github.com/CVLAB-Unibo/RefRec

2012.13720 2021-10-22 cs.CV 57%

Learning Inter- and Intraframe Representations for Non-Lambertian Photometric Stereo

Yanlong Cao, Binjie Ding, Zewei He, Jiangxin Yang, Jingxi Chen, Yanpeng Cao, Xin Li

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 9 pages,8 figures

2104.10291 2021-10-15 cs.CV 57%

Soft Expectation and Deep Maximization for Image Feature Detection

Alexander Mai, Allen Yang, Dominique E. Meyer

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 9 pages, 3 figures, 2 tables

2110.05839 2021-10-13 cs.CV 57%

PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation

Hualie Jiang, Laiyan Ding, Junjie Hu, Rui Huang

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments Accepted by 3DV 2021

2107.11010 2021-10-13 eess.IV cs.CV 57%

3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image

Bowen Hu, Baiying Lei, Shuqiang Wang, Yong Liu, Bingchuan Wang, Min Gan, Yanyan Shen

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2104.13135 2021-10-13 cs.CV 57%

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

Roberto Mecca, Fotios Logothetis, Ignas Budvytis, Roberto Cipolla

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2008.04933 2021-10-13 cs.CV 57%

PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks

Fotios Logothetis, Ignas Budvytis, Roberto Mecca, Roberto Cipolla

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2110.03851 2021-10-11 cs.CV 57%

Automatic annotation of visual deep neural networks

Ming Li, ChenHao Guo

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2110.02948 2021-10-07 cs.CV 57%

Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

Tianye Li, Shichen Liu, Timo Bolkart, Jiayi Liu, Hao Li, Yajie Zhao

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments International Conference on Computer Vision (ICCV)

1. 三维重建 4398 篇

Sparse Depth Completion with Semantic Mesh Deformation Optimization

Adversarial Parametric Pose Prior

Unimodal Face Classification with Multimodal Training

Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas

Wide-angle Image Rectification: A Survey

Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model

LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies

Medial Spectral Coordinates for 3D Shape Analysis

Towards Panoptic 3D Parsing for Single Image in the Wild

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction

Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

Deep Point Set Resampling via Gradient Fields

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

TMBuD: A dataset for urban scene building detection

Multimodal Semi-Supervised Learning for 3D Objects

Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction

Deep Permutation Equivariant Structure from Motion

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

Learning Inter- and Intraframe Representations for Non-Lambertian Photometric Stereo

Soft Expectation and Deep Maximization for Image Feature Detection

PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation

3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks

Automatic annotation of visual deep neural networks

Topologically Consistent Multi-View Face Inference Using Volumetric Sampling