3D 视觉 - arXivDaily 专题

2402.16994 2024-04-12 cs.CV cs.AI cs.GR cs.LG 62%

GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis

Dmitry Petrov, Pradyumn Goyal, Vikas Thamizharasan, Vladimir G. Kim, Matheus Gadelha, Melinos Averkiou, Siddhartha Chaudhuri, Evangelos Kalogerakis

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

Comments Webpage: https://lodurality.github.io/GEM3D/ -- Cond. accept. to SIGGRAPH 2024 (conf. track) -- Changes (based on reviews): changed style to sigconf; rearranged figures for readability; added missing citations; fixed misaligned centers in Fig. 3; added failure cases (Fig. 10); rewrote discussion; added categories averages to Tab. 8; added Tab. 10 with model capacities

2111.05778 2024-04-08 cs.GR cs.CG cs.CV 62%

Theoretical and Empirical Analysis of a Fast Algorithm for Extracting Polygons from Signed Distance Bounds

Nenad Markuš, Mirko Sužnjević

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

2404.03462 2024-04-05 cs.CV cs.RO 62%

You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects

Lei Zhou, Haozhe Wang, Zhengshen Zhang, Zhiyang Liu, Francis EH Tay, adn Marcelo H. Ang.

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

Comments ICRA 2024

2311.17024 2024-04-04 cs.CV cs.GR 62%

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features

Niladri Shekhar Dutt, Sanjeev Muralikrishnan, Niloy J. Mitra

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

Comments Accepted at CVPR'24

2403.18762 2024-03-28 cs.CV cs.AI cs.RO 62%

ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition

Weidong Xie, Lun Luo, Nanfei Ye, Yi Ren, Shaoyi Du, Minhang Wang, Jintao Xu, Rui Ai, Weihao Gu, Xieyuanli Chen

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

Comments 8 pages, 11 figures, conference

2306.07632 2024-03-27 cs.CV cs.GR 62%

NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering

Shi Mao, Chenming Wu, Zhelun Shen, Yifan Wang, Dayan Wu, Liangjun Zhang

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

2311.18287 2024-03-26 eess.IV cs.CV cs.GR 62%

Dispersed Structured Light for Hyperspectral 3D Imaging

Suhyun Shin, Seokjun Choi, Felix Heide, Seung-Hwan Baek

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

2403.15385 2024-03-25 cs.CV cs.AI cs.GR cs.LG 62%

LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis

Kevin Xie, Jonathan Lorraine, Tianshi Cao, Jun Gao, James Lucas, Antonio Torralba, Sanja Fidler, Xiaohui Zeng

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

Comments See the project website at https://research.nvidia.com/labs/toronto-ai/LATTE3D/

2403.10357 2024-03-20 cs.CV cs.GR 62%

ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image

Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Ziyan Wang, Chun-Han Yao, Marco Volino, Edmond Boyer, Adrian Hilton, Tony Tung

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

Comments Accepted to CVPR24; Project page: https://marcopesavento.github.io/ANIM/

2403.02037 2024-03-05 cs.CV cs.RO 62%

Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving

Yuxuan Liu

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

Comments HKUST PhD Thesis; https://github.com/Owen-Liuyuxuan/visionfactory

2311.12398 2024-02-20 cs.CV cs.RO 62%

RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation

Tutian Tang, Jiyu Liu, Jieyi Zhang, Haoyuan Fu, Wenqiang Xu, Cewu Lu

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

2402.06826 2024-02-13 cs.CV cs.RO 62%

Neural Rendering based Urban Scene Reconstruction for Autonomous Driving

Shihao Shen, Louis Kerofsky, Varun Ravi Kumar, Senthil Yogamani

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

Comments Accepted for publication in Electronic Imaging, Autonomous Vehicles and Machines 2024. Qualitative results are shared in https://youtu.be/EK47fYJiY3M

2401.05335 2024-01-11 cs.CV cs.GR cs.LG 62%

InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes

Mohamad Shahbazi, Liesbeth Claessens, Michael Niemeyer, Edo Collins, Alessio Tonioni, Luc Van Gool, Federico Tombari

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

2312.09249 2023-12-15 cs.CV cs.GR 62%

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Ruoxi Shi, Xinyue Wei, Cheng Wang, Hao Su

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

Comments Project page: https://sarahweiii.github.io/zerorf/

2312.08851 2023-12-15 cs.CV cs.CE cs.RO 62%

Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities

Runwei Guan, Haocheng Zhao, Shanliang Yao, Ka Lok Man, Xiaohui Zhu, Limin Yu, Yong Yue, Jeremy Smith, Eng Gee Lim, Weiping Ding, Yutao Yue

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

Comments 18 pages, 9 figures

2312.07964 2023-12-14 cs.RO cs.CV 62%

Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation

Jingwei Yang, Bohuan Xue, Yi Feng, Deming Wang, Rui Fan, Qijun Chen

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

2211.02760 2023-11-29 cs.RO cs.CV 62%

Development and evaluation of automated localisation and reconstruction of all fruits on tomato plants in a greenhouse based on multi-view perception and 3D multi-object tracking

David Rapado Rincon, Eldert J. van Henten, Gert Kootstra

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

2306.15670 2023-11-23 cs.CV cs.RO 62%

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

Haoyi Jiang, Tianheng Cheng, Naiyu Gao, Haoyang Zhang, Tianwei Lin, Wenyu Liu, Xinggang Wang

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

Comments Technical report. Code and models at: https://github.com/hustvl/Symphonies

2311.01267 2023-11-03 cs.RO cs.AI cs.CV 62%

UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding

Han Xue, Yutong Li, Wenqiang Xu, Huanyu Li, Dongzhe Zheng, Cewu Lu

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

Comments CoRL 2023

2310.09956 2023-10-17 cs.RO cs.CV 62%

Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Prior

Xiaotong Chen, Zheming Zhou, Zhuo Deng, Omid Ghasemalizadeh, Min Sun, Cheng-Hao Kuo, Arnie Sen

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

Comments IEEE-RAS Humanoids 2023 paper, 8 pages, 6 figures

2310.01228 2023-10-17 cs.CV cs.GR 62%

Reconstructing 3D Human Pose from RGB-D Data with Occlusions

Bowen Dang, Xi Zhao, Bowen Zhang, He Wang

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

2310.06577 2023-10-11 cs.CV cs.GR 62%

SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction

Fei Wang, Kongzhang Tang, Hefeng Wu, Baoquan Zhao, Hao Cai, Teng Zhou

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

Comments 9 pages, to appear in Pacific Graphics 2023

2305.12653 2023-10-10 cs.GR cs.CG cs.CV 62%

Estimating Discrete Total Curvature with Per Triangle Normal Variation

Crane He Chen

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

2309.11993 2023-09-22 cs.GR cs.CV 62%

Neural Stochastic Screened Poisson Reconstruction

Silvia Sellán, Alec Jacobson

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

2309.09118 2023-09-19 cs.CV cs.AI cs.RO 62%

Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors

Ziwei Liao, Jun Yang, Jingxing Qian, Angela P. Schoellig, Steven L. Waslander

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

Comments Manuscript submitted to ICRA 2024

2111.01082 2023-09-19 cs.CV cs.GR 62%

FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction

Hao Zhu, Haotian Yang, Longwei Guo, Yidi Zhang, Yanru Wang, Mingkai Huang, Menghua Wu, Qiu Shen, Ruigang Yang, Xun Cao

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

Comments Accepted to T-PAMI 2023; Extension of FaceScape(CVPR 2020); Code & data are available at https://github.com/zhuhao-nju/facescape

2309.06313 2023-09-13 cs.CV cs.LG cs.RO 62%

Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle

Maria Priisalu

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

2309.04581 2023-09-12 cs.GR cs.CV cs.LG 62%

Dynamic Mesh-Aware Radiance Fields

Yi-Ling Qiao, Alexander Gao, Yiran Xu, Yue Feng, Jia-Bin Huang, Ming C. Lin

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

Comments ICCV 2023

2109.04398 2023-09-07 cs.CV cs.AI cs.GR 62%

Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction

Zixiong Wang, Pengfei Wang, Pengshuai Wang, Qiujie Dong, Junjie Gao, Shuangmin Chen, Shiqing Xin, Changhe Tu, Wenping Wang

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

Journal ref IEEE Transactions on Visualization and Computer Graphics

2308.09865 2023-08-22 cs.CV cs.GR 62%

A Theory of Topological Derivatives for Inverse Rendering of Geometry

Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi

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

Comments ICCV 23; Project Page at https://ishit.github.io/td/

1. 三维重建 4398 篇

GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis

Theoretical and Empirical Analysis of a Fast Algorithm for Extracting Polygons from Signed Distance Bounds

You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features

ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition

NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering

Dispersed Structured Light for Hyperspectral 3D Imaging

LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis

ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image

Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving

RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation

Neural Rendering based Urban Scene Reconstruction for Autonomous Driving

InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities

Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation

Development and evaluation of automated localisation and reconstruction of all fruits on tomato plants in a greenhouse based on multi-view perception and 3D multi-object tracking

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding

Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Prior

Reconstructing 3D Human Pose from RGB-D Data with Occlusions

SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction

Estimating Discrete Total Curvature with Per Triangle Normal Variation

Neural Stochastic Screened Poisson Reconstruction

Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors

FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction

Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle

Dynamic Mesh-Aware Radiance Fields

Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction

A Theory of Topological Derivatives for Inverse Rendering of Geometry