3D 视觉 - arXivDaily 专题

2207.09686 2022-08-02 cs.CV 70%

Object-Compositional Neural Implicit Surfaces

Qianyi Wu, Xian Liu, Yuedong Chen, Kejie Li, Chuanxia Zheng, Jianfei Cai, Jianmin Zheng

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

Comments ECCV2022, Project Page: https://qianyiwu.github.io/objectsdf/ Code: https://github.com/QianyiWu/objsdf

2203.15946 2022-07-21 cs.CV cs.AI 70%

Towards Learning Neural Representations from Shadows

Kushagra Tiwary, Tzofi Klinghoffer, Ramesh Raskar

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

2206.12055 2022-06-27 cs.CV 70%

SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation

Xin-Yang Zheng, Yang Liu, Peng-Shuai Wang, Xin Tong

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

Comments Accepted to Computer Graphics Forum (SGP), 2022

2106.01907 2022-04-21 eess.IV cs.CV 70%

Robotic Inspection of Underground Utilities for Construction Survey Using a Ground Penetrating Radar

Jinglun Feng, Liang Yang, Ejup Hoxha, Jiang Biao, Jizhong Xiao

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

2204.03715 2022-04-11 cs.CV astro-ph.IM 70%

Gravitationally Lensed Black Hole Emission Tomography

Aviad Levis, Pratul P. Srinivasan, Andrew A. Chael, Ren Ng, Katherine L. Bouman

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

Comments To appear in the IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Supplemental material including accompanying pdf, code, and video highlight can be found in the project page: http://imaging.cms.caltech.edu/bhnerf/

2203.15235 2022-03-30 cs.CV 70%

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

Jihyun Lee, Minhyuk Sung, Hyunjin Kim, Tae-Kyun Kim

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

Comments 16 pages, 10 figures, accepted to CVPR 2022

2203.07967 2022-03-24 cs.CV cs.LG 70%

Intrinsic Neural Fields: Learning Functions on Manifolds

Lukas Koestler, Daniel Grittner, Michael Moeller, Daniel Cremers, Zorah Lähner

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

2203.10212 2022-03-22 cs.CV 70%

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

Haocheng Yuan, Chen Zhao, Shichao Fan, Jiaxi Jiang, Jiaqi Yang

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

2203.00952 2022-03-03 eess.IV cs.CV eess.SP 70%

Sketched RT3D: How to reconstruct billions of photons per second

Julián Tachella, Michael P. Sheehan, Mike E. Davies

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

Comments Accepted at ICASSP 2022

2202.13855 2022-03-01 cs.CV 70%

Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function

Haohao Hu, Hexing Yang, Jian Wu, Xiao Lei, Frank Bieder, Jan-Hendrik Pauls, Christoph Stiller

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

Comments 8 pages

2112.05300 2021-12-13 cs.CV cs.LG 70%

Representing 3D Shapes with Probabilistic Directed Distance Fields

Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

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

Comments 22 pages

2112.00202 2021-12-02 cs.CV 70%

3DVNet: Multi-View Depth Prediction and Volumetric Refinement

Alexander Rich, Noah Stier, Pradeep Sen, Tobias Höllerer

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

Comments 10 pages, 6 figures, 3 tables. Accepted to 3DV 2021

2110.11860 2021-10-25 cs.CV cs.AI cs.LG 70%

AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

Simon Giebenhain, Bastian Goldlücke

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

Comments Project code: https://github.com/SimonGiebenhain/AIR-Nets

2106.15446 2021-09-21 cs.RO 70%

Scalable and Elastic LiDAR Reconstruction in Complex Environments Through Spatial Analysis

Yiduo Wang, Milad Ramezani, Matias Mattamala, Maurice Fallon

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

Comments 8 pages, 9 figures, accepted for the 10th European Conference on Mobile Robots (ECMR2021)

2109.00512 2021-09-02 cs.CV 70%

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction

Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, David Novotny

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

Journal ref International Conference on Computer Vision, 2021

2108.05863 2021-08-13 cs.CV 70%

Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision

Xiaoshi Wu, Hadar Averbuch-Elor, Jin Sun, Noah Snavely

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

Comments Published in ICCV 2021; Project webpage: https://www.cs.cornell.edu/projects/babel/

2104.00024 2021-08-11 cs.CV 70%

RetrievalFuse: Neural 3D Scene Reconstruction with a Database

Yawar Siddiqui, Justus Thies, Fangchang Ma, Qi Shan, Matthias Nießner, Angela Dai

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

Comments Project Page: https://nihalsid.github.io/retrieval-fuse/

2004.00845 2021-07-13 cs.CV 70%

Occlusion-Aware Depth Estimation with Adaptive Normal Constraints

Xiaoxiao Long, Lingjie Liu, Christian Theobalt, Wenping Wang

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

Comments ECCV 2020

Journal ref ECCV 2020. Lecture Notes in Computer Science, vol 12354. Springer, Cham

2105.08016 2021-05-18 cs.CV cs.CG 70%

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

Ge Zhang, Or Litany, Srinath Sridhar, Leonidas Guibas

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

Comments preprint

2103.03390 2021-05-03 cs.CV cs.AI 70%

An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering

Nikola Zubić, Pietro Liò

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

Comments 21 page, 13 figures, 6 tables, to appear as a full paper with oral contribution in AIAI 2021

2012.10958 2021-05-03 cs.CV 70%

Towards Automatic Digital Documentation and Progress Reporting of Mechanical Construction Pipes using Smartphones

Reza Maalek, Derek Lichti, Shahrokh Maalek

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

2003.06523 2020-11-06 cs.CV 70%

Instant recovery of shape from spectrum via latent space connections

Riccardo Marin, Arianna Rampini, Umberto Castellani, Emanuele Rodolà, Maks Ovsjanikov, Simone Melzi

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

1912.04663 2020-08-18 cs.CV 70%

3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture

Kohei Yamashita, Shohei Nobuhara, Ko Nishino

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

Comments BMVC 2020

2007.02295 2020-07-07 cs.CV 70%

Multi view stereo with semantic priors

Elisavet Konstantina Stathopoulou, Fabio Remondino

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

2005.13312 2020-05-29 cs.CV 70%

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

Xin Chen, Yuwei Li, Xi Luo, Tianjia Shao, Jingyi Yu, Kun Zhou, Youyi Zheng

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

Comments 10 pages, 12 figures

Journal ref IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 3, pp. 1466-1475, 1 March 2020

2005.05125 2020-05-12 cs.CV 70%

FroDO: From Detections to 3D Objects

Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

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

Comments To be published in CVPR 2020. The first two authors contributed equally

2004.08029 2020-04-20 cs.CV cs.CR cs.HC 70%

Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality

Jaybie A. de Guzman, Kanchana Thilakarathna, Aruna Seneviratne

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

Comments 15 pages

2003.01456 2020-04-16 cs.CV cs.LG 70%

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

Julian Chibane, Thiemo Alldieck, Gerard Pons-Moll

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

Comments {IEEE} Conference on Computer Vision and Pattern Recognition (CVPR)2020

Journal ref {IEEE} Conference on Computer Vision and Pattern Recognition (CVPR) 2020

1904.06458 2019-08-27 cs.CV 70%

Transformable Bottleneck Networks

Kyle Olszewski, Sergey Tulyakov, Oliver Woodford, Hao Li, Linjie Luo

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

Comments Project Page: https://kyleolsz.github.io/TB-Networks/

1908.07475 2019-08-21 cs.CV 70%

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image

Roman Klokov, Jakob Verbeek, Edmond Boyer

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

Comments Accepted as Oral at BMVC'19

1. 三维重建 4390 篇

Object-Compositional Neural Implicit Surfaces

Towards Learning Neural Representations from Shadows

SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation

Robotic Inspection of Underground Utilities for Construction Survey Using a Ground Penetrating Radar

Gravitationally Lensed Black Hole Emission Tomography

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

Intrinsic Neural Fields: Learning Functions on Manifolds

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

Sketched RT3D: How to reconstruct billions of photons per second

Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function

Representing 3D Shapes with Probabilistic Directed Distance Fields

3DVNet: Multi-View Depth Prediction and Volumetric Refinement

AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

Scalable and Elastic LiDAR Reconstruction in Complex Environments Through Spatial Analysis

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction

Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision

RetrievalFuse: Neural 3D Scene Reconstruction with a Database

Occlusion-Aware Depth Estimation with Adaptive Normal Constraints

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering

Towards Automatic Digital Documentation and Progress Reporting of Mechanical Construction Pipes using Smartphones

Instant recovery of shape from spectrum via latent space connections

3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture

Multi view stereo with semantic priors

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

FroDO: From Detections to 3D Objects

Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

Transformable Bottleneck Networks

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image