3D 视觉 - arXivDaily 专题

2206.02840 2022-06-08 cs.RO cs.CV 62%

Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction

Sascha Arnold, Bilal Wehbe

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

Comments Preprint

Journal ref IEEE International Conference on Robotics and Automation (ICRA) 2022

2202.01999 2022-06-02 cs.CV cs.GR cs.LG 62%

Neural Dual Contouring

Zhiqin Chen, Andrea Tagliasacchi, Thomas Funkhouser, Hao Zhang

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

Comments Accepted to SIGGRAPH (journal) 2022. Code: https://github.com/czq142857/NDC

Journal ref Neural Dual Contouring. ACM Trans. Graph. 41, 4, Article 104 (July 2022), 13 pages

2205.15572 2022-06-01 cs.CV cs.GR 62%

3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies

Weikai Chen, Cheng Lin, Weiyang Li, Bo Yang

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

Comments Accepted to CVPR 2022

2205.14573 2022-05-31 cs.CV cs.AI cs.GR 62%

ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation

Haoxiang Guo, Shilin Liu, Hao Pan, Yang Liu, Xin Tong, Baining Guo

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

Comments This article is published by ACM Trans. Graph. (SIGGRAPH 2022). This is the author's preprint version

2109.03349 2022-05-31 cs.CV cs.RO math.OC 62%

Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization

Heng Yang, Luca Carlone

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

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022

2201.10326 2022-05-24 cs.CV cs.GR cs.LG 62%

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

Xingguang Yan, Liqiang Lin, Niloy J. Mitra, Dani Lischinski, Daniel Cohen-Or, Hui Huang

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

Comments Project page: https://shapeformer.github.io/

2205.07479 2022-05-17 cs.CV cs.RO 62%

Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments

Ekta U. Samani, Ashis G. Banerjee

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

Comments Accepted for presentation in the IEEE International Conference on Robotics and Automation (ICRA) 2022 Workshop on Robotic Perception and Mapping: Emerging Techniques

2202.08345 2022-05-11 cs.CV cs.GR 62%

Learning Smooth Neural Functions via Lipschitz Regularization

Hsueh-Ti Derek Liu, Francis Williams, Alec Jacobson, Sanja Fidler, Or Litany

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

2106.14193 2022-04-12 cs.CV cs.RO 62%

SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

Haitao Lin, Zichang Liu, Chilam Cheang, Yanwei Fu, Guodong Guo, Xiangyang Xue

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

Comments accepted by CVPR2022

2204.03105 2022-04-08 cs.CV cs.GR cs.LG 62%

AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis

Zhiqin Chen, Kangxue Yin, Sanja Fidler

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

Comments CVPR 2022. Project page: https://nv-tlabs.github.io/AUV-NET

2111.14465 2022-04-08 cs.CV cs.AI cs.GR cs.LG 62%

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos

Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Marc Pollefeys

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

Comments CVPR 2022 camera-ready

Journal ref 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

2111.11426 2022-04-07 cs.CV cs.GR cs.LG 62%

Neural Fields in Visual Computing and Beyond

Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar

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

Comments Equal advising: Vincent Sitzmann and Srinath Sridhar

2204.02091 2022-04-06 cs.CV cs.AI cs.LG cs.RO 62%

P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior

Vaishakh Patil, Christos Sakaridis, Alexander Liniger, Luc Van Gool

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

Comments Accepted at CVPR 2022

2112.04481 2022-04-05 cs.CV cs.GR 62%

What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction

Nilesh Kulkarni, Justin Johnson, David F. Fouhey

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

Comments Updated illustrations for method section. Project Page see https://nileshkulkarni.github.io/scene_drdf

2203.02884 2022-04-01 cs.CV cs.RO 62%

Towards Self-Supervised Category-Level Object Pose and Size Estimation

Yisheng He, Haoqiang Fan, Haibin Huang, Qifeng Chen, Jian Sun

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

2112.05381 2022-03-31 cs.CV cs.GR 62%

UNIST: Unpaired Neural Implicit Shape Translation Network

Qimin Chen, Johannes Merz, Aditya Sanghi, Hooman Shayani, Ali Mahdavi-Amiri, Hao Zhang

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

Comments CVPR 2022. project page: https://qiminchen.github.io/unist/

2203.03609 2022-03-30 cs.CV cs.AI cs.GR 62%

Human-Aware Object Placement for Visual Environment Reconstruction

Hongwei Yi, Chun-Hao P. Huang, Dimitrios Tzionas, Muhammed Kocabas, Mohamed Hassan, Siyu Tang, Justus Thies, Michael J. Black

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

Comments Accepted by CVPR2022

2104.06392 2022-03-24 cs.GR cs.AI cs.CV cs.LG 62%

ShapeMOD: Macro Operation Discovery for 3D Shape Programs

R. Kenny Jones, David Charatan, 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 SIGGRAPH 2021. Project Page: https://rkjones4.github.io/shapeMOD.html

2203.11938 2022-03-23 cs.CV cs.GR 62%

ϕ-SfT: Shape-from-Template with a Physics-Based Deformation Model

Navami Kairanda, Edith Tretschk, Mohamed Elgharib, Christian Theobalt, Vladislav Golyanik

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

Comments 11 pages, 8 figures and one table; Computer Vision and Pattern Recognition (CVPR) 2022

2111.09383 2022-03-23 cs.CV cs.GR 62%

DeepCurrents: Learning Implicit Representations of Shapes with Boundaries

David Palmer, Dmitriy Smirnov, Stephanie Wang, Albert Chern, Justin Solomon

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

2203.09149 2022-03-18 cs.RO cs.CV 62%

Active Visuo-Haptic Object Shape Completion

Lukas Rustler, Jens Lundell, Jan Kristof Behrens, Ville Kyrki, Matej Hoffmann

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

Comments 8 pages, 7 figures

Journal ref IEEE Robotics and Automation Letters 7 (2) 2022, 5254-5261

2112.05999 2022-03-11 cs.CV cs.AI cs.GR 62%

Curvature-guided dynamic scale networks for Multi-view Stereo

Khang Truong Giang, Soohwan Song, Sungho Jo

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

Comments Accepted to ICLR 2022

2201.10865 2022-03-09 cs.CV cs.RO 62%

On the Issues of TrueDepth Sensor Data for Computer Vision Tasks Across Different iPad Generations

Steffen Urban, Thomas Lindemeier, David Dobbelstein, Matthias Haenel

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

Comments 17 pages

2203.02554 2022-03-08 cs.CV cs.AI cs.GR cs.LG 62%

Building 3D Generative Models from Minimal Data

Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum

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

Comments arXiv admin note: substantial text overlap with arXiv:2011.12440

2203.01929 2022-03-04 cs.CV cs.LG cs.RO 62%

CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation

Muhammad Zubair Irshad, Thomas Kollar, Michael Laskey, Kevin Stone, Zsolt Kira

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

Comments Accepted to ICRA 2022, Project page with videos: https://zubair-irshad.github.io/projects/CenterSnap.html

2203.00051 2022-03-02 cs.CV cs.GR 62%

ERF: Explicit Radiance Field Reconstruction From Scratch

Samir Aroudj, Steven Lovegrove, Eddy Ilg, Tanner Schmidt, Michael Goesele, Richard Newcombe

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

Comments 23 pages, 18 figures

1912.07109 2022-02-23 cs.CV cs.GR cs.LG 62%

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Yue Jiang, Dantong Ji, Zhizhong Han, Matthias Zwicker

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

Comments CVPR2020 Full Paper (Oral Top 5%)

2111.09526 2022-02-22 cs.CV cs.GR 62%

Learning Modified Indicator Functions for Surface Reconstruction

Dong Xiao, Siyou Lin, Zuoqiang Shi, Bin Wang

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

Comments Accepted by Computers & Graphics from SMI 2021

2202.02171 2022-02-07 cs.CV cs.GR eess.IV 62%

NeAT: Neural Adaptive Tomography

Darius Rückert, Yuanhao Wang, Rui Li, Ramzi Idoughi, Wolfgang Heidrich

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

2112.07022 2022-01-24 cs.GR cs.CV cs.LG 62%

Learning Body-Aware 3D Shape Generative Models

Bryce Blinn, Alexander Ding, R. Kenny Jones, Manolis Savva, Srinath Sridhar, Daniel Ritchie

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

Comments 11 pages, 8 figures

1. 三维重建 4393 篇

Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction

Neural Dual Contouring

3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies

ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation

Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments

Learning Smooth Neural Functions via Lipschitz Regularization

SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos

Neural Fields in Visual Computing and Beyond

P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior

What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction

Towards Self-Supervised Category-Level Object Pose and Size Estimation

UNIST: Unpaired Neural Implicit Shape Translation Network

Human-Aware Object Placement for Visual Environment Reconstruction

ShapeMOD: Macro Operation Discovery for 3D Shape Programs

ϕ-SfT: Shape-from-Template with a Physics-Based Deformation Model

DeepCurrents: Learning Implicit Representations of Shapes with Boundaries

Active Visuo-Haptic Object Shape Completion

Curvature-guided dynamic scale networks for Multi-view Stereo

On the Issues of TrueDepth Sensor Data for Computer Vision Tasks Across Different iPad Generations

Building 3D Generative Models from Minimal Data

CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation

ERF: Explicit Radiance Field Reconstruction From Scratch

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Learning Modified Indicator Functions for Surface Reconstruction

NeAT: Neural Adaptive Tomography

Learning Body-Aware 3D Shape Generative Models