3D 视觉 - arXivDaily 专题

2012.01203 2021-05-07 cs.CV cs.GR 62%

Learning Delaunay Surface Elements for Mesh Reconstruction

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov

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

Journal ref CVPR 2021

1912.01438 2021-04-27 cs.CV cs.RO 62%

FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation

Zirui Wang, Shuda Li, Henry Howard-Jenkins, Victor Adrian Prisacariu, Min Chen

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

Comments WACV 2020

2103.15349 2021-04-20 cs.RO cs.CV 62%

Refractive Light-Field Features for Curved Transparent Objects in Structure from Motion

Dorian Tsai, Peter Corke, Thierry Peynot, Donald G. Dansereau

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

Comments submitted to IROS-RAL 2021. 8 pages, 9 figures, 2 tables

2104.07660 2021-04-16 cs.CV cs.GR 62%

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

Qianli Ma, Shunsuke Saito, Jinlong Yang, Siyu Tang, Michael J. Black

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

Comments In CVPR 2021. Project page: https://qianlim.github.io/SCALE

2012.06434 2021-04-13 cs.CV cs.GR 62%

Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations

Wang Yifan, Shihao Wu, Cengiz Oztireli, Olga Sorkine-Hornung

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

Comments CVPR 2021 code: https://github.com/yifita/iso-points

2103.14794 2021-03-30 cs.CV cs.GR 62%

Learning Efficient Photometric Feature Transform for Multi-view Stereo

Kaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma, Ping Tan, Hongzhi Wu, Kun Zhou

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

2011.09594 2021-03-30 cs.CV cs.RO 62%

Deep Multi-view Depth Estimation with Predicted Uncertainty

Tong Ke, Tien Do, Khiem Vuong, Kourosh Sartipi, Stergios I. Roumeliotis

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

Comments IEEE International Conference on Robotics and Automation (ICRA 2021)

2008.01068 2021-03-15 cs.CV cs.GR 62%

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

Peng-Shuai Wang, Yu-Qi Yang, Qian-Fang Zou, Zhirong Wu, Yang Liu, Xin Tong

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

Comments Accepted by AAAI 2021. Code: https://github.com/microsoft/O-CNN/blob/master/docs/unsupervised.md

2012.09235 2021-03-11 cs.CV cs.GR cs.LG 62%

Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong, Feng Liu, Xiaoming Liu, Michael M. Bronstein, Stefanos Zafeiriou

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

Comments In review with International Journal of Computer Vision (IJCV) - Revision 1 (minor revision)

1811.07791 2021-03-02 cs.CV cs.AI cs.GR cs.LG cs.SE 62%

Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image

David Fuentes-Jimenez, David Casillas-Perez, Daniel Pizarro, Toby Collins, Adrien Bartoli

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

2003.04651 2021-02-10 cs.GR cs.CV 62%

Enabling Viewpoint Learning through Dynamic Label Generation

Michael Schelling, Pedro Hermosilla, Pere-Pau Vazquez, Timo Ropinski

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

2008.01639 2021-02-08 cs.CV cs.GR 62%

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollhöfer, Carsten Stoll, Christian Theobalt

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

Comments 25 pages, including supplementary material. Code: https://github.com/edgar-tr/patchnets Project page: https://gvv.mpi-inf.mpg.de/projects/PatchNets/

2006.02535 2021-01-26 cs.CV cs.GR 62%

A Survey on Deep Learning Techniques for Stereo-based Depth Estimation

Hamid Laga, Laurent Valentin Jospin, Farid Boussaid, Mohammed Bennamoun

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

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

2101.06409 2021-01-19 cs.CV cs.RO 62%

Shape Back-Projection In 3D Scenes

Ashish Kumar, L. Behera

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

Comments 7 pages, 7 figures, 3 tables

2012.01451 2020-12-04 cs.CV cs.GR cs.LG 62%

Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction

Aljaž Božič, Pablo Palafox, Michael Zollhöfer, Justus Thies, Angela Dai, Matthias Nießner

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

Comments Video: https://youtu.be/vyq36eFkdWo

2011.14669 2020-12-01 cs.CV cs.RO 62%

Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration

Yiming Wang, Alessio Del Bue

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

Comments published on European Conference on Computer Vision, 2020

2004.07414 2020-11-26 cs.CV cs.GR cs.LG stat.ML 62%

Combinatorial 3D Shape Generation via Sequential Assembly

Jungtaek Kim, Hyunsoo Chung, Jinhwi Lee, Minsu Cho, Jaesik Park

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

Comments 14 pages, 20 figures, 1 table, presented at NeurIPS 2020 Workshop on Machine Learning for Engineering Modeling, Simulation, and Design

2011.09390 2020-11-19 cs.RO cs.CV 62%

Diverse Plausible Shape Completions from Ambiguous Depth Images

Brad Saund, Dmitry Berenson

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

2010.12796 2020-10-27 cs.CV cs.RO 62%

Improving the generalization of network based relative pose regression: dimension reduction as a regularizer

Xiaqing Ding, Yue Wang, Li Tang, Yanmei Jiao, Rong Xiong

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

2010.09774 2020-10-21 cs.CV cs.CG cs.GR cs.LG 62%

GAMesh: Guided and Augmented Meshing for Deep Point Networks

Nitin Agarwal, M Gopi

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

Comments Accepted to 3DV 2020

2010.09582 2020-10-20 cs.CV cs.LG cs.RO eess.IV 62%

Learning to Reconstruct and Segment 3D Objects

Bo Yang

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

Comments DPhil (PhD) Thesis 2020, University of Oxford https://ora.ox.ac.uk/objects/uuid:5f9cd30d-0ee7-412d-ba49-44f5fd76bf28

2006.06769 2020-10-20 math.OC cs.CV cs.RO 62%

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

Heng Yang, Luca Carlone

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

Comments NeurIPS 2020. 9 pages main results, 34 pages total. Code available at https://github.com/MIT-SPARK/CertifiablyRobustPerception

Journal ref 34th Conference on Neural Information Processing Systems (NeurIPS 2020)

2001.05613 2020-10-15 cs.CV cs.RO 62%

Synergetic Reconstruction from 2D Pose and 3D Motion for Wide-Space Multi-Person Video Motion Capture in the Wild

Takuya Ohashi, Yosuke Ikegami, Yoshihiko Nakamura

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

Journal ref Image and Vision Computing, Volume 104, 2020

2006.05400 2020-10-06 cs.CV cs.GR cs.LG 62%

SALD: Sign Agnostic Learning with Derivatives

Matan Atzmon, Yaron Lipman

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

2009.08026 2020-09-21 cs.GR cs.CV cs.LG 62%

ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis

R. Kenny Jones, Theresa Barton, Xianghao Xu, Kai Wang, Ellen Jiang, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie

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

Comments Accepted to Siggraph Asia 2020; project page: https://rkjones4.github.io/shapeAssembly.html

2008.03875 2020-08-11 cs.CV cs.GR cs.LG 62%

RocNet: Recursive Octree Network for Efficient 3D Deep Representation

Juncheng Liu, Steven Mills, Brendan McCane

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

2006.02068 2020-08-07 cs.CV cs.RO 62%

PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation

Noriaki Hirose, Satoshi Koide, Keisuke Kawano, Ruho Kondo

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

Comments 13 pages, 8 figures, 3 tables

1905.10290 2020-08-05 cs.CV cs.GR 62%

DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects

Edgar Tretschk, Ayush Tewari, Michael Zollhöfer, Vladislav Golyanik, Christian Theobalt

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

Comments 27 pages, including supplementary material

2007.08501 2020-07-17 cs.CV cs.GR cs.LG 62%

Accelerating 3D Deep Learning with PyTorch3D

Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, Georgia Gkioxari

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

Comments tech report

2006.14374 2020-07-17 cs.CV cs.RO 62%

Discontinuous and Smooth Depth Completion with Binary Anisotropic Diffusion Tensor

Yasuhiro Yao, Menandro Roxas, Ryoichi Ishikawa, Shingo Ando, Jun Shimamura, Takeshi Oishi

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

Comments 8 pages 6 figures

1. 三维重建 4393 篇

Learning Delaunay Surface Elements for Mesh Reconstruction

FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation

Refractive Light-Field Features for Curved Transparent Objects in Structure from Motion

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations

Learning Efficient Photometric Feature Transform for Multi-view Stereo

Deep Multi-view Depth Estimation with Predicted Uncertainty

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image

Enabling Viewpoint Learning through Dynamic Label Generation

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

A Survey on Deep Learning Techniques for Stereo-based Depth Estimation

Shape Back-Projection In 3D Scenes

Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction

Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration

Combinatorial 3D Shape Generation via Sequential Assembly

Diverse Plausible Shape Completions from Ambiguous Depth Images

Improving the generalization of network based relative pose regression: dimension reduction as a regularizer

GAMesh: Guided and Augmented Meshing for Deep Point Networks

Learning to Reconstruct and Segment 3D Objects

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

Synergetic Reconstruction from 2D Pose and 3D Motion for Wide-Space Multi-Person Video Motion Capture in the Wild

SALD: Sign Agnostic Learning with Derivatives

ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis

RocNet: Recursive Octree Network for Efficient 3D Deep Representation

PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation

DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects

Accelerating 3D Deep Learning with PyTorch3D

Discontinuous and Smooth Depth Completion with Binary Anisotropic Diffusion Tensor