3D 视觉 - arXivDaily 专题

2002.10099 2020-07-10 cs.LG cs.CV cs.GR stat.ML 62%

Implicit Geometric Regularization for Learning Shapes

Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, Yaron Lipman

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

Comments 37th International Conference on Machine Learning, Vienna, Austria, 2020

1912.04302 2020-06-23 cs.CV cs.AI cs.GR 62%

DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data

Aljaž Božič, Michael Zollhöfer, Christian Theobalt, Matthias Nießner

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

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

2005.11084 2020-06-16 cs.GR cs.CV cs.LG 62%

Point2Mesh: A Self-Prior for Deformable Meshes

Rana Hanocka, Gal Metzer, Raja Giryes, Daniel Cohen-Or

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

Comments SIGGRAPH 2020; Project page: https://ranahanocka.github.io/point2mesh/

1909.08605 2020-06-15 cs.CV cs.RO math.OC 62%

Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection

Heng Yang, Pasquale Antonante, Vasileios Tzoumas, Luca Carlone

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

Comments 10 pages, 5 figures, published at IEEE Robotics and Automation Letters (RA-L), 2020, Best Paper Award in Robot Vision at ICRA 2020

Journal ref IEEE Robotics and Automation Letters (RA-L), 2020

2006.02098 2020-06-04 cs.CV cs.LG cs.RO 62%

GFPNet: A Deep Network for Learning Shape Completion in Generic Fitted Primitives

Tiberiu Cocias, Alexandru Razvant, Sorin Grigorescu

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

Comments 8 pages, 14 figures, IEEE Robotics and Automation Letters. Preprint Version. Accepted May, 2020

1910.11669 2020-05-22 cs.RO cs.CV 62%

Learning Task-Oriented Grasping from Human Activity Datasets

Mia Kokic, Danica Kragic, Jeannette Bohg

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

Journal ref IEEE Robotics and Automation Letters 5 (2020) 3352-3359

2005.05751 2020-05-13 cs.GR cs.CV cs.LG 62%

Unpaired Motion Style Transfer from Video to Animation

Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

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

Comments SIGGRAPH 2020. Project page: https://deepmotionediting.github.io/style_transfer , Video: https://www.youtube.com/watch?v=m04zuBSdGrc , Code: https://github.com/DeepMotionEditing/deep-motion-editing

2004.12232 2020-04-28 cs.CV cs.RO eess.IV 62%

Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image

Aniket Pokale, Aditya Aggarwal, K. Madhava Krishna

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

Comments 8 pages, 5 figures, 2 tables

1911.10949 2020-04-27 cs.CV cs.GR cs.LG 62%

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

Rundi Wu, Yixin Zhuang, Kai Xu, Hao Zhang, Baoquan Chen

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

Comments Accepted to CVPR 2020. Code available at https://github.com/ChrisWu1997/PQ-NET

1911.12012 2020-04-21 cs.CV cs.LG cs.RO 62%

Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

Shuo Cheng, Zexiang Xu, Shilin Zhu, Zhuwen Li, Li Erran Li, Ravi Ramamoorthi, Hao Su

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

Comments Accepted to CVPR 2020 (Oral)

2004.04572 2020-04-14 cs.GR cs.CV cs.LG eess.IV 62%

ARCH: Animatable Reconstruction of Clothed Humans

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

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

Comments 10 pages, 10 figures, CVPR2020

1909.05736 2020-04-14 cs.CV cs.GR cs.LG 62%

CvxNet: Learnable Convex Decomposition

Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi

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

2004.04242 2020-04-10 cs.CV cs.GR 62%

Deep Manifold Prior

Matheus Gadelha, Rui Wang, Subhransu Maji

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

Comments 22 pages, 12 figures

2004.03572 2020-04-08 cs.CV cs.RO 62%

Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation

Jiaming Sun, Linghao Chen, Yiming Xie, Siyu Zhang, Qinhong Jiang, Xiaowei Zhou, Hujun Bao

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

Comments Accepted to CVPR 2020. Code is available at https://github.com/zju3dv/disprcnn

1911.10414 2020-04-02 cs.CV cs.GR cs.LG 62%

SAL: Sign Agnostic Learning of Shapes from Raw Data

Matan Atzmon, Yaron Lipman

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

Comments Accepted to CVPR 2020

1911.09204 2020-04-02 cs.GR cs.CV 62%

DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction

Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong, Hao Zhang

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

2003.06518 2020-03-27 cs.RO cs.CV 62%

Leveraging Vision and Kinematics Data to Improve Realism of Biomechanic Soft-tissue Simulation for Robotic Surgery

Jie Ying Wu, Peter Kazanzides, Mathias Unberath

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

Comments 12 pages, 4 figures, to be published in IJCARS IPCAI special edition 2020

1912.05012 2020-03-03 cs.CV cs.RO 62%

Deep-Learning Assisted High-Resolution Binocular Stereo Depth Reconstruction

Yaoyu Hu, Weikun Zhen, Sebastian Scherer

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

Comments Submitted to International Conference on Robotics and Automation (ICRA2020)

1809.07917 2020-02-27 cs.CV cs.GR 62%

Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes

Peng-Shuai Wang, Chun-Yu Sun, Yang Liu, Xin Tong

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

Journal ref ACM Transactions on Graphics, 2018

1909.09548 2020-02-07 cs.RO cs.CV 62%

An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environments

Lukas Schmid, Michael Pantic, Raghav Khanna, Lionel Ott, Roland Siegwart, Juan Nieto

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

Comments 8 pages, 6 figures, video: https://youtu.be/lEadqJ1_8Do, framework: https://github.com/ethz-asl/mav_active_3d_planning

Journal ref IEEE Robotics and Automation Letters, Vol. 5, Iss. 2, April 2020

1912.03880 2019-12-11 cs.RO cs.CV 62%

Video Motion Capture from the Part Confidence Maps of Multi-Camera Images by Spatiotemporal Filtering Using the Human Skeletal Model

Takuya Ohashi, Yosuke Ikegami, Kazuki Yamamoto, Wataru Takano, Yoshihiko Nakamura

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

Comments International Conference on Intelligent Robots and Systems (IROS), 2018

1906.06543 2019-11-28 cs.CV cs.CG cs.GR cs.LG 62%

Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Xian-Feng Han, Hamid Laga, Mohammed Bennamoun

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

Comments arXiv admin note: text overlap with arXiv:1806.06098, arXiv:1712.06584, arXiv:1804.10975 by other authors

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, Nov. 2019

1911.00767 2019-11-05 cs.CV cs.GR 62%

Learning to Infer Implicit Surfaces without 3D Supervision

Shichen Liu, Shunsuke Saito, Weikai Chen, Hao Li

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

1910.02738 2019-10-08 cs.CV cs.RO cs.SY eess.SY 62%

An Interactive Control Approach to 3D Shape Reconstruction

Bipul Islam, Ji Liu, Anthony Yezzi, Romeil Sandhu

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

1910.02066 2019-10-07 cs.RO cs.CV 62%

Higher Order Function Networks for View Planning and Multi-View Reconstruction

Selim Engin, Eric Mitchell, Daewon Lee, Volkan Isler, Daniel D. Lee

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

Comments 7 pages, 6 figures

1909.06585 2019-09-18 cs.RO cs.CV 62%

Deep Robotic Prediction with hierarchical RGB-D Fusion

Yaoxian Song, Jun Wen, Yuejiao Fei, Changbin Yu

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

Comments 8 pages, 8 figures, submit to ICRA2020

1812.02822 2019-09-18 cs.GR cs.CV cs.LG 62%

Learning Implicit Fields for Generative Shape Modeling

Zhiqin Chen, Hao Zhang

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

Comments Accepted to CVPR 2019. Code: https://github.com/czq142857/implicit-decoder Project page: https://www.sfu.ca/~zhiqinc/imgan/Readme.html

1909.06980 2019-09-17 cs.RO cs.CV 62%

kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completion

Wei Gao, Russ Tedrake

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

Comments In submission. The video demo and source code are available on https://sites.google.com/view/generalizable-manipulation/

1908.08185 2019-08-23 cs.CV cs.GR eess.IV 62%

Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion

Chunyu Li, Yusuke Monno, Hironori Hidaka, Masatoshi Okutomi

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

Comments Accepted by ICCV 2019. Project homepage: http://www.ok.sc.e.titech.ac.jp/res/PCSSfM/

1908.00575 2019-08-05 cs.GR cs.CG cs.CV 62%

StructureNet: Hierarchical Graph Networks for 3D Shape Generation

Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas

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

Comments Conditionally Accepted to Siggraph Asia 2019

1. 三维重建 4393 篇

Implicit Geometric Regularization for Learning Shapes

DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data

Point2Mesh: A Self-Prior for Deformable Meshes

Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection

GFPNet: A Deep Network for Learning Shape Completion in Generic Fitted Primitives

Learning Task-Oriented Grasping from Human Activity Datasets

Unpaired Motion Style Transfer from Video to Animation

Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

ARCH: Animatable Reconstruction of Clothed Humans

CvxNet: Learnable Convex Decomposition

Deep Manifold Prior

Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation

SAL: Sign Agnostic Learning of Shapes from Raw Data

DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction

Leveraging Vision and Kinematics Data to Improve Realism of Biomechanic Soft-tissue Simulation for Robotic Surgery

Deep-Learning Assisted High-Resolution Binocular Stereo Depth Reconstruction

Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes

An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environments

Video Motion Capture from the Part Confidence Maps of Multi-Camera Images by Spatiotemporal Filtering Using the Human Skeletal Model

Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Learning to Infer Implicit Surfaces without 3D Supervision

An Interactive Control Approach to 3D Shape Reconstruction

Higher Order Function Networks for View Planning and Multi-View Reconstruction

Deep Robotic Prediction with hierarchical RGB-D Fusion

Learning Implicit Fields for Generative Shape Modeling

kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completion

Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion

StructureNet: Hierarchical Graph Networks for 3D Shape Generation