3D 视觉 - arXivDaily 专题

2210.05250 2022-10-12 cs.GR cs.NA math.NA 57%

Digital twins for city simulation: Automatic, efficient, and robust mesh generation for large-scale city modeling and simulation

Vasilis Naserentin, Anders Logg

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

2210.03158 2022-10-10 cs.CV cs.AI 57%

Neural Volumetric Mesh Generator

Yan Zheng, Lemeng Wu, Xingchao Liu, Zhen Chen, Qiang Liu, Qixing Huang

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

2210.02382 2022-10-06 cs.CV 57%

NeuralMeshing: Differentiable Meshing of Implicit Neural Representations

Mathias Vetsch, Sandro Lombardi, Marc Pollefeys, Martin R. Oswald

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

Comments This preprint has not undergone any post-submission improvements or corrections. The Version of Record of this contribution is published in "44th DAGM German Conference on Pattern Recognition (GCPR 2022), Konstanz, Germany, September 27-30, 2022, Proceedings", and is available at https://doi.org/10.1007/978-3-031-16788-1_20

2210.01721 2022-10-05 cs.CV cs.AI cs.LG 57%

MBW: Multi-view Bootstrapping in the Wild

Mosam Dabhi, Chaoyang Wang, Tim Clifford, Laszlo Attila Jeni, Ian R. Fasel, Simon Lucey

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

Comments NeurIPS 2022 conference. Project webpage and code: https://github.com/mosamdabhi/MBW

2209.08345 2022-10-05 cs.CV 57%

Shape Completion with Points in the Shadow

Bowen Zhang, Xi Zhao, He Wang, Ruizhen Hu

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

Comments SIGGRAPH Aisa 2022 Conference Paper

2209.13362 2022-09-28 cs.CV 57%

DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image

Yijin Li, Xinyang Liu, Wenqi Dong, Han Zhou, Hujun Bao, Guofeng Zhang, Yinda Zhang, Zhaopeng Cui

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

Comments Accepted to ECCV 2022. Project Page: https://zju3dv.github.io/deltar/

2209.13159 2022-09-28 cs.RO 57%

Efficient View Path Planning for Autonomous Implicit Reconstruction

Jing Zeng, Yanxu Li, Yunlong Ran, Shuo Li, Fei Gao, Lincheng Li, Shibo He, Jiming chen, Qi Ye

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

2112.02082 2022-09-28 cs.CV 57%

Geometry-aware Two-scale PIFu Representation for Human Reconstruction

Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson W. H. Lau

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

Comments Accepted by NeurIPS 2022. 20 pages, 20 figures

2209.10621 2022-09-23 cs.CV 57%

GNPM: Geometric-Aware Neural Parametric Models

Mirgahney Mohamed, Lourdes Agapito

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

Comments 10 pages, 8 figures

2206.15236 2022-09-22 cs.GR 57%

Stochastic Poisson Surface Reconstruction

Silvia Sellán, Alec Jacobson

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

2204.03353 2022-09-22 cs.CV 57%

Learning Online Multi-Sensor Depth Fusion

Erik Sandström, Martin R. Oswald, Suryansh Kumar, Silvan Weder, Fisher Yu, Cristian Sminchisescu, Luc Van Gool

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

Comments Accepted to ECCV 2022. 31 pages, 17 figures, 15 Tables

2209.09733 2022-09-21 eess.IV cs.CV 57%

Metal Inpainting in CBCT Projections Using Score-based Generative Model

Siyuan Mei, Fuxin Fan, Andreas Maier

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

2209.09231 2022-09-20 cs.CV 57%

3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling

Yu-Ting Yen, Chia-Ni Lu, Wei-Chen Chiu, Yi-Hsuan Tsai

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

Comments Accepted in ECCV 2022. Project page: https://ccc870206.github.io/3D-PL/

2209.08241 2022-09-20 cs.CV 57%

Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps

Saed Moradi, Alireza Memarmoghadam, Denis Laurendeau

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

2209.06926 2022-09-16 cs.CV 57%

End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes

Qiao Chen, Charalambos Poullis

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

Comments IEEE International Conference on Signal Processing, Sensors, and Intelligent Systems (SPSIS 2022)

2209.06562 2022-09-15 cs.CV 57%

INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices

Torben Fetzer, Gerd Reis, Didier Stricker

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

Comments 18 pages, 15 figures, datasets available at https://www.dfki.uni-kl.de/~fetzer/flow2pose.html

2209.05612 2022-09-14 cs.CV 57%

Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges

Sanjay Haresh, Xiaohao Sun, Hanxiao Jiang, Angel X. Chang, Manolis Savva

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

Comments 3DV 2022

2209.02152 2022-09-08 cs.CV cs.LG 57%

Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations

Pan He, Patrick Emami, Sanjay Ranka, Anand Rangarajan

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

Comments Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

2209.02485 2022-09-07 cs.CV cs.CL 57%

Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

Xi Wang, Gen Li, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan, Otmar Hilliges

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

2208.13241 2022-09-07 cs.CV 57%

Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image

Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Simon Chen, Yifan Liu, Chunhua Shen

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

Comments 20 pages. Journal version of the conference paper "Learning to Recover 3D Scene Shape from a Single Image". arXiv admin note: substantial text overlap with arXiv:2012.09365

2201.09025 2022-09-05 cs.RO 57%

SL Sensor: An Open-Source, ROS-Based, Real-Time Structured Light Sensor for High Accuracy Construction Robotic Applications

Teng Foong Lam, Hermann Blum, Roland Siegwart, Abel Gawel

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

Journal ref Automation in Construction Volume 142, 2022, pg. 104424

2206.05837 2022-09-02 cs.CV 57%

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

Trevor Houchens, Cheng-You Lu, Shivam Duggal, Rao Fu, Srinath Sridhar

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

2205.05335 2022-08-30 cs.CV 57%

Deep Depth Completion from Extremely Sparse Data: A Survey

Junjie Hu, Chenyu Bao, Mete Ozay, Chenyou Fan, Qing Gao, Honghai Liu, Tin Lun Lam

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

2203.13296 2022-08-29 cs.CV 57%

RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers

Michał J. Tyszkiewicz, Kevis-Kokitsi Maninis, Stefan Popov, Vittorio Ferrari

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

Comments ECCV 2022 camera ready

2205.11480 2022-08-22 physics.ins-det cs.CV physics.atom-ph physics.optics quant-ph 57%

Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Clouds

Sanha Cheong, Josef C. Frisch, Sean Gasiorowski, Jason M. Hogan, Michael Kagan, Murtaza Safdari, Ariel Schwartzman, Maxime Vandegar

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

Journal ref 2022 JINST 17 P08021

2201.12184 2022-08-19 cs.CV cs.LG eess.IV 57%

A tomographic workflow to enable deep learning for X-ray based foreign object detection

Mathé T. Zeegers, Tristan van Leeuwen, Daniël M. Pelt, Sophia Bethany Coban, Robert van Liere, Kees Joost Batenburg

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

Comments This paper is under consideration at Expert Systems with Applications. 22 pages, 15 figures

Journal ref Expert Systems with Applications 206 (2022) 117768

2208.06661 2022-08-16 cs.CV 57%

SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation

Ruida Zhang, Yan Di, Fabian Manhardt, Federico Tombari, Xiangyang Ji

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

Comments Accepted by IROS 2022

2208.05350 2022-08-11 cs.CV 57%

MD-Net: Multi-Detector for Local Feature Extraction

Emanuele Santellani, Christian Sormann, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer

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

Comments Accepted at ICPR 2022

2208.03167 2022-08-08 cs.CV 57%

Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment

Xue Hu, Xinghui Li, Benjamin Busam, Yiren Zhou, Ales Leonardis, Shanxin Yuan

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

2012.10296 2022-08-02 cs.CV 57%

Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion

Lam Huynh, Phong Nguyen-Ha, Jiri Matas, Esa Rahtu, Janne Heikkila

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

Comments 10 pages, 9 figures

1. 三维重建 4401 篇

Digital twins for city simulation: Automatic, efficient, and robust mesh generation for large-scale city modeling and simulation

Neural Volumetric Mesh Generator

NeuralMeshing: Differentiable Meshing of Implicit Neural Representations

MBW: Multi-view Bootstrapping in the Wild

Shape Completion with Points in the Shadow

DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image

Efficient View Path Planning for Autonomous Implicit Reconstruction

Geometry-aware Two-scale PIFu Representation for Human Reconstruction

GNPM: Geometric-Aware Neural Parametric Models

Stochastic Poisson Surface Reconstruction

Learning Online Multi-Sensor Depth Fusion

Metal Inpainting in CBCT Projections Using Score-based Generative Model

3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling

Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps

End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes

INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices

Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges

Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations

Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image

SL Sensor: An Open-Source, ROS-Based, Real-Time Structured Light Sensor for High Accuracy Construction Robotic Applications

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

Deep Depth Completion from Extremely Sparse Data: A Survey

RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers

Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Clouds

A tomographic workflow to enable deep learning for X-ray based foreign object detection

SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation

MD-Net: Multi-Detector for Local Feature Extraction

Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment

Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion