3D 视觉 - arXivDaily 专题

2106.15328 2021-07-30 cs.CV 57%

Deep Learning for Multi-View Stereo via Plane Sweep: A Survey

Qingtian Zhu, Chen Min, Zizhuang Wei, Yisong Chen, Guoping Wang

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

2107.12512 2021-07-28 cs.CV cs.AI 57%

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

Eduard Ramon, Gil Triginer, Janna Escur, Albert Pumarola, Jaime Garcia, Xavier Giro-i-Nieto, Francesc Moreno-Noguer

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

2107.12492 2021-07-28 cs.RO 57%

SpectGRASP: Robotic Grasping by Spectral Correlation

Maxime Adjigble, Cristiana de Farias, Rustam Stolkin, Naresh Marturi

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

Comments Accepted for 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): September 27 - October 1, Prague, Czech Republic (Online)

2107.04644 2021-07-24 eess.IV cs.CV 57%

Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images

Baoru Huang, Jianqing Zheng, Anh Nguyen, David Tuch, Kunal Vyas, Stamatia Giannarou, Daniel S. Elson

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

2107.10563 2021-07-23 eess.IV cs.CV 57%

Fristograms: Revealing and Exploiting Light Field Internals

Thorsten Herfet, Kelvin Chelli, Tobias Lange, Robin Kremer

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

Comments 6 pages, 7 figures

2107.08067 2021-07-20 cs.RO cs.AI 57%

DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulation

Bao Thach, Alan Kuntz, Tucker Hermans

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

Comments Published at RSS 2021 Workshop on Deformable Object Simulation in Robotics; received Honorable Mention for Best Paper Award

2009.03871 2021-07-14 cs.CV cs.LG 57%

Intraoperative Liver Surface Completion with Graph Convolutional VAE

Simone Foti, Bongjin Koo, Thomas Dowrick, Joao Ramalhinho, Moustafa Allam, Brian Davidson, Danail Stoyanov, Matthew J. Clarkson

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

2107.04867 2021-07-13 cs.CV 57%

Learning 3D Dense Correspondence via Canonical Point Autoencoder

An-Chieh Cheng, Xueting Li, Min Sun, Ming-Hsuan Yang, Sifei Liu

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

2107.04622 2021-07-13 cs.CV 57%

Cumulative Assessment for Urban 3D Modeling

Shea Hagstrom, Hee Won Pak, Stephanie Ku, Sean Wang, Gregory Hager, Myron Brown

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

Comments Published in IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2021

2107.00005 2021-07-12 cs.CV 57%

Extraction of Key-frames of Endoscopic Videos by using Depth Information

Pradipta Sasmal, Avinash Paul, M. K. Bhuyan, Yuji Iwahori

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

Journal ref The paper is under consideration at Pattern Recognition Letters, Elsevier, 2021

2106.16237 2021-07-08 cs.CV 57%

Multimodal Shape Completion via IMLE

Himanshu Arora, Saurabh Mishra, Shichong Peng, Ke Li, Ali Mahdavi-Amiri

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

Comments Project Website: https://sites.google.com/site/alimahdaviamiri/projects/shape-completion

2107.02493 2021-07-07 cs.CV 57%

Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting

Xiaomeng Chu, Jiajun Deng, Yao Li, Zhenxun Yuan, Yanyong Zhang, Jianmin Ji, Yu Zhang

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

Comments Accepted by ACM Multimedia 2021

2103.04216 2021-06-29 cs.CV 57%

Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction

Wei Yin, Yifan Liu, Chunhua Shen

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

Comments Fxied typos. Extended version of arXiv:1907.12209 Int. Conf. Comp. Vis. (ICCV) 2019. Code is available at: https://git.io/Depth. arXiv admin note: substantial text overlap with arXiv:2002.00569

2106.11725 2021-06-23 cs.CV 57%

RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

Jiayi Wang, Franziska Mueller, Florian Bernard, Suzanne Sorli, Oleksandr Sotnychenko, Neng Qian, Miguel A. Otaduy, Dan Casas, Christian Theobalt

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

Comments SIGGRAPH Asia 2020

Journal ref ACM Transactions on Graphics (TOG) 39 (6), 1-16, 2020

2106.10635 2021-06-22 cs.CV 57%

FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM

Yijie Wu, Fan Xue

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

2106.09336 2021-06-18 cs.CV 57%

THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers

Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu

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

2012.05522 2021-06-15 cs.CV 57%

Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Jiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu, Xiaolong Wang

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

2008.06910 2021-06-15 cs.CV 57%

Neural Descent for Visual 3D Human Pose and Shape

Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu

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

Comments CVPR 2021

2106.06629 2021-06-15 cs.CV 57%

Mirror3D: Depth Refinement for Mirror Surfaces

Jiaqi Tan, Weijie Lin, Angel X. Chang, Manolis Savva

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

Comments Paper presented at CVPR 2021. For code, data and pretrained models, see https://3dlg-hcvc.github.io/mirror3d/

2106.05662 2021-06-11 cs.CV 57%

To The Point: Correspondence-driven monocular 3D category reconstruction

Filippos Kokkinos, Iasonas Kokkinos

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

2010.06217 2021-06-10 cs.GR 57%

TM-NET: Deep Generative Networks for Textured Meshes

Lin Gao, Tong Wu, Yu-Jie Yuan, Ming-Xian Lin, Yu-Kun Lai, Hao Zhang

专题命中三维重建：novel view synthesis(abstract)；分类 cs.GR

2106.03505 2021-06-08 cs.CV 57%

Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos

Shaocheng Jia, Xin Pei, Wei Yao, S. C. Wong

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

2105.14355 2021-06-01 cs.CV eess.IV 57%

Three-dimensional multimodal medical imaging system based on free-hand ultrasound and structured light

Jhacson Meza, Sonia H. Contreras-Ortiz, Lenny A. Romero, Andres G. Marrugo

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

Journal ref Optical Engineering 60(5), 054106 (2021)

2105.13575 2021-05-31 cs.CV cs.AI 57%

2nd Place Solution for IJCAI-PRICAI 2020 3D AI Challenge: 3D Object Reconstruction from A Single Image

Yichen Cao, Yufei Wei, Shichao Liu, Lin Xu

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

Comments 5 pages, 2 figures, 5 tables

Journal ref IJCAI 2020 workshop

2105.11352 2021-05-25 cs.CV 57%

Reconstructing Small 3D Objects in front of a Textured Background

Petr Hruby, Tomas Pajdla

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

Comments 36 pages total: 11 pages paper and 25 pages supplementary

2011.13388 2021-05-19 cs.CV cs.LG 57%

3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer

Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari

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

2011.14565 2021-05-14 cs.CV 57%

Deep Implicit Templates for 3D Shape Representation

Zerong Zheng, Tao Yu, Qionghai Dai, Yebin Liu

专题命中三维重建：3D vision(abstract)；分类 cs.CV

2010.10959 2021-05-03 cs.CV 57%

Learning to Guide Local Feature Matches

François Darmon, Mathieu Aubry, Pascal Monasse

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

Comments Accepted to 3DV 2020

2104.14554 2021-04-30 cs.CV cs.LG 57%

MongeNet: Efficient Sampler for Geometric Deep Learning

Léo Lebrat, Rodrigo Santa Cruz, Clinton Fookes, Olivier Salvado

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

2006.14660 2021-04-29 cs.CV 57%

SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans

Angela Dai, Yawar Siddiqui, Justus Thies, Julien Valentin, Matthias Nießner

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

Comments Video: https://youtu.be/1cj962m9zqo

1. 三维重建 4395 篇

Deep Learning for Multi-View Stereo via Plane Sweep: A Survey

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

SpectGRASP: Robotic Grasping by Spectral Correlation

Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images

Fristograms: Revealing and Exploiting Light Field Internals

DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulation

Intraoperative Liver Surface Completion with Graph Convolutional VAE

Learning 3D Dense Correspondence via Canonical Point Autoencoder

Cumulative Assessment for Urban 3D Modeling

Extraction of Key-frames of Endoscopic Videos by using Depth Information

Multimodal Shape Completion via IMLE

Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting

Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction

RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video

FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM

THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers

Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Neural Descent for Visual 3D Human Pose and Shape

Mirror3D: Depth Refinement for Mirror Surfaces

To The Point: Correspondence-driven monocular 3D category reconstruction

TM-NET: Deep Generative Networks for Textured Meshes

Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos

Three-dimensional multimodal medical imaging system based on free-hand ultrasound and structured light

2nd Place Solution for IJCAI-PRICAI 2020 3D AI Challenge: 3D Object Reconstruction from A Single Image

Reconstructing Small 3D Objects in front of a Textured Background

3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer

Deep Implicit Templates for 3D Shape Representation

Learning to Guide Local Feature Matches

MongeNet: Efficient Sampler for Geometric Deep Learning

SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans