3D 视觉 - arXivDaily 专题

2412.11033 2024-12-17 cs.CV 57%

AURORA: Automated Unleash of 3D Room Outlines for VR Applications

Huijun Han, Yongqing Liang, Yuanlong Zhou, Wenping Wang, Edgar J. Rojas-Munoz, Xin Li

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

Comments 8 pages, 4 figures

2408.01579 2024-12-17 cs.CV 57%

THOR2: Topological Analysis for 3D Shape and Color-Based Human-Inspired Object Recognition in Unseen Environments

Ekta U. Samani, Ashis G. Banerjee

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

2310.07997 2024-12-17 cs.CV cs.AI 57%

PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction

Chen Zhang, Wanjuan Su, Qingshan Xu, Wenbing Tao

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

Journal ref IEEE Transactions on Visualization and Computer Graphics. 2024

2412.09043 2024-12-13 cs.CV 57%

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

Hao Lu, Tianshuo Xu, Wenzhao Zheng, Yunpeng Zhang, Wei Zhan, Dalong Du, Masayoshi Tomizuka, Kurt Keutzer, Yingcong Chen

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

2407.00574 2024-12-13 cs.CV 57%

Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery

Fengyuan Yang, Kerui Gu, Ha Linh Nguyen, Tze Ho Elden Tse, Angela Yao

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

Comments 13 pages, 11 figures, 6 tables

2412.08684 2024-12-13 cs.CV eess.IV 57%

Coherent3D: Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan, Michael Stengel, Henry Fuchs, Shalini De Mello, Koki Nagano

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

Comments arXiv admin note: substantial text overlap with arXiv:2405.00794

2412.03928 2024-12-13 cs.CV cs.AI cs.HC cs.LG 57%

MT3DNet: Multi-Task learning Network for 3D Surgical Scene Reconstruction

Mithun Parab, Pranay Lendave, Jiyoung Kim, Thi Quynh Dan Nguyen, Palash Ingle

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

Comments 1. Notation Update: Added * for equal contribution, ensuring proper attribution. 2. Subsection Fix: Removed the `subsection` tag for Section 3.1 (no 3.2 existed), maintaining content but fixing hierarchy. 3. Text Additions: Added lines in Section 5 and Subsection 4.2 for clarity, with references for better context

2308.03492 2024-12-12 cs.CV 57%

Learning Photometric Feature Transform for Free-form Object Scan

Xiang Feng, Kaizhang Kang, Fan Pei, Huakeng Ding, Jinjiang You, Ping Tan, Kun Zhou, Hongzhi Wu

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

2412.07230 2024-12-11 cs.CV 57%

Deep Non-rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Hui Deng, Jiawei Shi, Zhen Qin, Yiran Zhong, Yuchao Dai

专题命中三维重建：3D vision(abstract)；分类 cs.CV

Comments 9 pages main text, 7 pages appendix

2003.11846 2024-12-10 eess.IV cs.CV 57%

Weakly-supervised 3D coronary artery reconstruction from two-view angiographic images

Lu Wang, Dong-xue Liang, Xiao-lei Yin, Jing Qiu, Zhi-yun Yang, Jun-hui Xing, Jian-zeng Dong, Zhao-yuan Ma

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

Comments We believe that this article lacks sufficient research depth and requires substantial revisions

2410.00348 2024-12-10 cs.CV 57%

Revisiting the Role of Texture in 3D Person Re-identification

Huy Nguyen, Kien Nguyen, Akila Pemasiri, Sridha Sridharan, Clinton Fookes

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

Comments Withdraw for major revision

2412.05274 2024-12-09 cs.CV 57%

SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images

Jiahua Dong, Tong Wu, Rui Qian, Jiaqi Wang

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

2412.04649 2024-12-09 cs.RO 57%

Generating Whole-Body Avoidance Motion through Localized Proximity Sensing

Simone Borelli, Francesco Giovinazzo, Francesco Grella, Giorgio Cannata

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

Comments Submitted for evaluation at the IEEE/ASME Transactions on Mechatronics Journal

2412.03571 2024-12-05 cs.CV 57%

Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation

Bingjie Song, Xin Huang, Ruting Xie, Xue Wang, Qing Wang

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

2412.03570 2024-12-05 cs.CV 57%

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis

Qitao Zhao, Shubham Tulsiani

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

Comments NeurIPS 2024. Project website: https://qitaozhao.github.io/SparseAGS

2412.03518 2024-12-05 cs.CV 57%

Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter

Hermes McGriff, Renato Martins, Nicolas Andreff, Cedric Demonceaux

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

2412.03512 2024-12-05 cs.CV 57%

Distillation of Diffusion Features for Semantic Correspondence

Frank Fundel, Johannes Schusterbauer, Vincent Tao Hu, Björn Ommer

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

Comments WACV 2025, Page: https://compvis.github.io/distilldift

2412.02317 2024-12-04 cs.CV 57%

HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset

Zedong Chu, Feng Xiong, Meiduo Liu, Jinzhi Zhang, Mingqi Shao, Zhaoxu Sun, Di Wang, Mu Xu

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

Comments Website: https://github.com/c8241998/HumanRig

2412.01855 2024-12-04 eess.IV cs.CV 57%

Volumetric Reconstruction of Prostatectomy Specimens from Histology

Tom Bisson, Isil Dogan O, Iris Piwonski, Tim-Rasmus Kiehl, Georg Lukas Baumgärtner, Rita Carvalho, Peter Hufnagl, Tobias Penzkofer, Norman Zerbe, Sefer Elezkurtaj

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

2412.00731 2024-12-03 cs.CV 57%

Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention

Ajith Balakrishnan, Sreeja S, Linu Shine

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

Comments ICVGIP-2024, 8 pages

2412.00511 2024-12-03 eess.IV cs.AI cs.CV 57%

Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI

Yanke Wang, Yolanne Y. R. Lee, Aurelio Dolfini, Markus Reischl, Ender Konukoglu, Kyriakos Flouris

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

Journal ref MICCAI Workshop on Deep Generative Models, 2024

2406.07648 2024-12-03 cs.CV 57%

Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention

Mengfei Li, Xiaoxiao Long, Yixun Liang, Weiyu Li, Yuan Liu, Peng Li, Wenhan Luo, Wenping Wang, Yike Guo

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

2411.19102 2024-12-02 cs.CV 57%

360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images

Zhongmiao Yan, Qi Wu, Songpengcheng Xia, Junyuan Deng, Xiang Mu, Renbiao Jin, Ling Pei

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

2407.21341 2024-12-02 cs.CV 57%

High-throughput 3D shape completion of potato tubers on a harvester

Pieter M. Blok, Federico Magistri, Cyrill Stachniss, Haozhou Wang, James Burridge, Wei Guo

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

Comments 20 pages, 11 figures, 6 tables

Journal ref Computers and Electronics in Agriculture, 228 (2025)

2411.18807 2024-12-02 cs.CV cs.CL 57%

Reconstructing Animals and the Wild

Peter Kulits, Michael J. Black, Silvia Zuffi

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

Comments 12 pages; project page: https://raw.is.tue.mpg.de/

2311.10708 2024-11-28 cs.CV cs.LG 57%

SelfEval: Leveraging the discriminative nature of generative models for evaluation

Sai Saketh Rambhatla, Ishan Misra

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

2307.07693 2024-11-25 cs.CV 57%

Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging

Meng Ye, Dong Yang, Mikael Kanski, Leon Axel, Dimitris Metaxas

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

Comments Accepted by ICCV 2023

2405.14342 2024-11-22 cs.CV 57%

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

Zhiheng Feng, Wenhua Wu, Tianchen Deng, Hesheng Wang

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

2411.13019 2024-11-21 cs.CV 57%

Open-World Amodal Appearance Completion

Jiayang Ao, Yanbei Jiang, Qiuhong Ke, Krista A. Ehinger

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

2410.11187 2024-11-21 cs.CV 57%

Multiview Scene Graph

Juexiao Zhang, Gao Zhu, Sihang Li, Xinhao Liu, Haorui Song, Xinran Tang, Chen Feng

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

Comments NeurIPS 2024. Website at https://ai4ce.github.io/MSG/

1. 三维重建 4394 篇

AURORA: Automated Unleash of 3D Room Outlines for VR Applications

THOR2: Topological Analysis for 3D Shape and Color-Based Human-Inspired Object Recognition in Unseen Environments

PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery

Coherent3D: Coherent 3D Portrait Video Reconstruction via Triplane Fusion

MT3DNet: Multi-Task learning Network for 3D Surgical Scene Reconstruction

Learning Photometric Feature Transform for Free-form Object Scan

Deep Non-rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Weakly-supervised 3D coronary artery reconstruction from two-view angiographic images

Revisiting the Role of Texture in 3D Person Re-identification

SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images

Generating Whole-Body Avoidance Motion through Localized Proximity Sensing

Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis

Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter

Distillation of Diffusion Features for Semantic Correspondence

HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset

Volumetric Reconstruction of Prostatectomy Specimens from Histology

Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention

Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI

Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention

360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images

High-throughput 3D shape completion of potato tubers on a harvester

Reconstructing Animals and the Wild

SelfEval: Leveraging the discriminative nature of generative models for evaluation

Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

Open-World Amodal Appearance Completion

Multiview Scene Graph