3D 视觉 - arXivDaily 专题

2112.14298 2021-12-30 cs.CV cs.RO 62%

Multimodal perception for dexterous manipulation

Guanqun Cao, Shan Luo

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

Comments 19 pages, 10 figures

2106.01970 2021-12-23 cs.CV cs.GR 62%

NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination

Xiuming Zhang, Pratul P. Srinivasan, Boyang Deng, Paul Debevec, William T. Freeman, Jonathan T. Barron

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

Comments Camera-ready version for SIGGRAPH Asia 2021. Project Page: https://people.csail.mit.edu/xiuming/projects/nerfactor/

2112.05644 2021-12-13 cs.CV cs.GR 62%

Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms

Kai Wang, Xianghao Xu, Leon Lei, Selena Ling, Natalie Lindsay, Angel X. Chang, Manolis Savva, Daniel Ritchie

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

Comments Symposium on Geometry Processing (SGP) 2021

Journal ref Computer Graphics Forum, 40: 57-69 (2021)

2111.13663 2021-11-29 cs.CV cs.LG cs.RO 62%

3D shape sensing and deep learning-based segmentation of strawberries

Justin Le Louëdec, Grzegorz Cielniak

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

Comments 14 pages, 13 figures, accepted to Computers and Electronics in Agriculture

Journal ref Computers and Electronics in Agriculture, Volume 190, November 2021, 106374

2111.03062 2021-11-05 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 62%

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning

Wenlong Huang, Igor Mordatch, Pieter Abbeel, Deepak Pathak

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

Comments Website at https://huangwl18.github.io/geometry-dex

2106.01553 2021-10-29 cs.CV cs.GR 62%

Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, Xin Tong

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

Comments Accepted by IJCAI 2021; Code: https://github.com/microsoft/SplinePosEnc

2107.09584 2021-10-27 cs.CV cs.RO 62%

Active 3D Shape Reconstruction from Vision and Touch

Edward J. Smith, David Meger, Luis Pineda, Roberto Calandra, Jitendra Malik, Adriana Romero, Michal Drozdzal

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

Journal ref Published at Neurips 2021

2108.09481 2021-10-25 cs.CV cs.RO 62%

DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

Jingwen Wang, Martin Rünz, Lourdes Agapito

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

Comments To be published at 3DV 2021

2109.01137 2021-10-20 cs.CV cs.GR 62%

The Power of Points for Modeling Humans in Clothing

Qianli Ma, 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 ICCV 2021. Project page: https://qianlim.github.io/POP

2110.05433 2021-10-12 cs.GR cs.CV cs.LG 62%

Mesh Draping: Parametrization-Free Neural Mesh Transfer

Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung, Daniel Cohen-Or

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

Comments 12 pages. Portions of this work previously appeared as arXiv:2104.09125v1 which has been split into two works: arXiv:2104.09125v2+ and this work

2110.04431 2021-10-12 cs.CV cs.GR 62%

SOMA: Solving Optical Marker-Based MoCap Automatically

Nima Ghorbani, Michael J. Black

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

Comments ICCV 2021

2011.12440 2021-10-04 cs.CV cs.GR 62%

Building 3D Morphable Models from a Single Scan

Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum

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

Comments ICCV Workshops: 1st Workshop on Traditional Computer Vision in the Age of Deep Learning (TradiCV)

2109.14821 2021-10-01 cs.CV cs.RO 62%

Semantic Dense Reconstruction with Consistent Scene Segments

Yingcai Wan, Yanyan Li, Yingxuan You, Cheng Guo, Lijin Fang, Federico Tombari

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

2109.14203 2021-09-30 cs.CV cs.GR 62%

Identity-Expression Ambiguity in 3D Morphable Face Models

Bernhard Egger, Skylar Sutherland, Safa C. Medin, Joshua Tenenbaum

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

Comments IEEE International Conference on Automatic Face and Gesture Recognition 2021

2108.12958 2021-08-31 cs.CV cs.AI cs.GR 62%

3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations

Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, Sanja Fidler

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

Comments Accepted to ICCV 2021. Supplementary material can be found on the project page: https://nv-tlabs.github.io/3DStyleNet/

2108.11305 2021-08-26 cs.CV cs.GR cs.LG 62%

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, Shuai Yi

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

Comments Accepted to ICCV 2021

2106.02994 2021-08-25 cs.CV cs.LG cs.RO 62%

Learning Topology from Synthetic Data for Unsupervised Depth Completion

Alex Wong, Safa Cicek, Stefano Soatto

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

2108.09895 2021-08-24 cs.RO cs.CV 62%

Burst Imaging for Light-Constrained Structure-From-Motion

Ahalya Ravendran, Mitch Bryson, Donald G. Dansereau

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

Comments 8 pages, 8 figures, 2 tables, for associated project page, see: https://roboticimaging.org/Projects/BurstSfM/

2107.14790 2021-08-17 cs.CV cs.DC cs.GR 62%

Out-of-Core Surface Reconstruction via Global $TGV$ Minimization

Nikolai Poliarnyi

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

Comments Accepted to the 2021 IEEE/CVF International Conference on Computer Vision (ICCV 2021)

2105.09492 2021-08-17 cs.CV cs.GR cs.LG 62%

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

Rundi Wu, Chang Xiao, Changxi Zheng

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

Comments Accepted to ICCV 2021. Code and data are available at http://www.cs.columbia.edu/cg/deepcad/

2108.04886 2021-08-12 cs.GR cs.CV 62%

Differentiable Surface Rendering via Non-Differentiable Sampling

Forrester Cole, Kyle Genova, Avneesh Sud, Daniel Vlasic, Zhoutong Zhang

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

Comments Accepted to ICCV 2021

2108.01411 2021-08-04 cs.CV cs.GR 62%

HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population

Ivan Kostiuk, Przemysław Stachura, Sławomir K. Tadeja, Tomasz Trzciński, Przemysław Spurek

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

2107.13452 2021-07-29 cs.CV cs.GR 62%

CarveNet: Carving Point-Block for Complex 3D Shape Completion

Qing Guo, Zhijie Wang, Felix Juefei-Xu, Di Lin, Lei Ma, Wei Feng, Yang Liu

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

Comments 10 pages and 10 figures

2103.05368 2021-07-23 cs.CV cs.RO 62%

ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments

Jin-Man Park, Jae-Hyuk Jang, Sahng-Min Yoo, Sun-Kyung Lee, Ue-Hwan Kim, Jong-Hwan Kim

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

Comments Accepted to IROS 2021

2107.09965 2021-07-22 cs.CV cs.GR 62%

Fabrication-Aware Reverse Engineering for Carpentry

James Noeckel, Haisen Zhao, Brian Curless, Adriana Schulz

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

Comments 24 pages, plus 6 pages of supplemental material. 14 figures. To be published in Eurographics Symposium on Geometry Processing, Volume 40 (2021), Number 5

2107.02191 2021-07-07 cs.CV cs.GR cs.LG 62%

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

Aljaž Božič, Pablo Palafox, 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/LIpTKYfKSqw

2106.13679 2021-06-29 cs.CV cs.GR cs.LG 62%

Shape registration in the time of transformers

Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà

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

2106.08851 2021-06-17 cs.RO cs.CV 62%

GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger

Shaoxiong Wang, Yu She, Branden Romero, Edward Adelson

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

Comments ICRA 2021

2106.05779 2021-06-16 cs.CV cs.GR 62%

Deep Implicit Surface Point Prediction Networks

Rahul Venkatesh, Tejan Karmali, Sarthak Sharma, Aurobrata Ghosh, R. Venkatesh Babu, László A. Jeni, Maneesh Singh

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

Comments 22 pages, 17 figures

2105.02976 2021-05-10 cs.CV cs.GR 62%

LASR: Learning Articulated Shape Reconstruction from a Monocular Video

Gengshan Yang, Deqing Sun, Varun Jampani, Daniel Vlasic, Forrester Cole, Huiwen Chang, Deva Ramanan, William T. Freeman, Ce Liu

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

Comments CVPR 2021. Project page: https://lasr-google.github.io/

1. 三维重建 4393 篇

Multimodal perception for dexterous manipulation

NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination

Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms

3D shape sensing and deep learning-based segmentation of strawberries

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning

Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Active 3D Shape Reconstruction from Vision and Touch

DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

The Power of Points for Modeling Humans in Clothing

Mesh Draping: Parametrization-Free Neural Mesh Transfer

SOMA: Solving Optical Marker-Based MoCap Automatically

Building 3D Morphable Models from a Single Scan

Semantic Dense Reconstruction with Consistent Scene Segments

Identity-Expression Ambiguity in 3D Morphable Face Models

3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Learning Topology from Synthetic Data for Unsupervised Depth Completion

Burst Imaging for Light-Constrained Structure-From-Motion

Out-of-Core Surface Reconstruction via Global $TGV$ Minimization

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

Differentiable Surface Rendering via Non-Differentiable Sampling

HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population

CarveNet: Carving Point-Block for Complex 3D Shape Completion

ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments

Fabrication-Aware Reverse Engineering for Carpentry

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

Shape registration in the time of transformers

GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger

Deep Implicit Surface Point Prediction Networks

LASR: Learning Articulated Shape Reconstruction from a Monocular Video