3D 视觉 - arXivDaily 专题

2310.09503 2024-01-26 cs.CV 57%

JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues

Jiayi Ji, Haowei Wang, Changli Wu, Yiwei Ma, Xiaoshuai Sun, Rongrong Ji

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 16 pages, 4 figures, 10 tables, 3D understanding

2308.02982 2024-01-26 cs.CV 57%

Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation

Haowei Wang, Jiji Tang, Jiayi Ji, Xiaoshuai Sun, Rongsheng Zhang, Yiwei Ma, Minda Zhao, Lincheng Li, zeng zhao, Tangjie Lv, Rongrong Ji

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ACM MM 2023, 3D Understanding, JM3D

2401.13416 2024-01-25 cs.RO 57%

Characterizing Perspective Error in Voxel-Based Lidar Scan Matching

Jason Rife, Matthew McDermott

专题命中点云：point cloud(abstract)；分类 cs.RO

Journal ref NAVIGATION, 71(1) 2024

2310.07189 2024-01-24 cs.CV 57%

SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition

Hongwei Ren, Yue Zhou, Yulong Huang, Haotian Fu, Xiaopeng Lin, Jie Song, Bojun Cheng

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ICLR 2024 (Spotlight)

2401.12051 2024-01-23 cs.CV cs.AI 57%

CloSe: A 3D Clothing Segmentation Dataset and Model

Dimitrije Antić, Garvita Tiwari, Batuhan Ozcomlekci, Riccardo Marin, Gerard Pons-Moll

专题命中点云：point cloud(abstract)；分类 cs.CV

2311.00928 2024-01-23 cs.RO 57%

Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAM

Hyungtae Lim, Beomsoo Kim, Daebeom Kim, Eungchang Mason Lee, Hyun Myung

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 26 pages, 23 figures

2303.07064 2024-01-23 cs.CV cs.AI 57%

A Generalized Multi-Modal Fusion Detection Framework

Leichao Cui, Xiuxian Li, Min Meng, Xiaoyu Mo

专题命中点云：point cloud(abstract)；分类 cs.CV

2401.11499 2024-01-23 cs.CV 57%

Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals

Shaoheng Fang, Zuhong Liu, Mingyu Wang, Chenxin Xu, Yiqi Zhong, Siheng Chen

专题命中点云：point cloud(abstract)；分类 cs.CV

2401.08720 2024-01-18 cs.CV 57%

Unsupervised Pre-Training for 3D Leaf Instance Segmentation

Gianmarco Roggiolani, Federico Magistri, Tiziano Guadagnino, Jens Behley, Cyrill Stachniss

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 7 images, RA-L

Journal ref IEEE Robotics and Automation Letters (RA-L), vol. 8, pp. 7448-7455, 2023

2304.07486 2024-01-18 cs.CV 57%

Region-Enhanced Feature Learning for Scene Semantic Segmentation

Xin Kang, Chaoqun Wang, Xuejin Chen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by IEEE Transactions on Multimedia 2023

2401.08562 2024-01-17 math.OC cs.CV 57%

Registration of algebraic varieties using Riemannian optimization

Florentin Goyens, Coralia Cartis, Stéphane Chrétien

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.06244 2024-01-17 cs.CV 57%

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion

Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra

专题命中点云：point cloud(abstract)；分类 cs.CV

2401.06145 2024-01-15 cs.DC cs.CV cs.LG cs.PF 57%

Minuet: Accelerating 3D Sparse Convolutions on GPUs

Jiacheng Yang, Christina Giannoula, Jun Wu, Mostafa Elhoushi, James Gleeson, Gennady Pekhimenko

专题命中点云：point cloud(abstract)；分类 cs.CV

2210.08159 2024-01-12 cs.CV 57%

Dynamics-aware Adversarial Attack of Adaptive Neural Networks

An Tao, Yueqi Duan, Yingqi Wang, Jiwen Lu, Jie Zhou

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:2112.09428

Journal ref IEEE Transactions on Circuits and Systems for Video Technology, 2024

2310.08261 2024-01-11 cs.CV 57%

GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection

Ziying Song, Haiyue Wei, Lin Bai, Lei Yang, Caiyan Jia

专题命中点云：point cloud(abstract)；分类 cs.CV

2308.13694 2024-01-11 cs.RO 57%

Correcting Motion Distortion for LIDAR HD-Map Localization

Matthew McDermott, Jason Rife

专题命中点云：point cloud(abstract)；分类 cs.RO

2401.04230 2024-01-10 cs.CV 57%

SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling

Chengjie Huang, Vahdat Abdelzad, Sean Sedwards, Krzysztof Czarnecki

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by WACV 2024

2301.00970 2024-01-09 cs.CV 57%

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

Xu Yan, Chaoda Zheng, Ying Xue, Zhen Li, Shuguang Cui, Dengxin Dai

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments IJCV-2024. The benchmark will be made available at https://yanx27.github.io/RobustLidarSeg/

2401.02550 2024-01-08 cs.CV 57%

OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision

Rahul Ahuja, Chris Baker, Wilko Schwarting

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at the proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

2212.00344 2024-01-08 cs.RO eess.SP 57%

Bayesian Heuristics for Robust Spatial Perception

Aamir Hussain Chughtai, Muhammad Tahir, Momin Uppal

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 10 pages, 8 figures

2203.01577 2024-01-04 cs.CV 57%

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

Yunze Liu, Yun Liu, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, Li Yi

专题命中点云：point cloud(abstract)；分类 cs.CV

Journal ref CVPR2022

2206.02597 2024-01-04 cs.RO cs.SE 57%

No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets

Alvari Seppänen, Eerik Alamikkotervo, Risto Ojala, Giacomo Dario, Kari Tammi

专题命中点云：point cloud(abstract)；分类 cs.RO

2401.00708 2024-01-02 cs.CV eess.IV 57%

Revisiting Nonlocal Self-Similarity from Continuous Representation

Yisi Luo, Xile Zhao, Deyu Meng

专题命中点云：point cloud(abstract)；分类 cs.CV

2312.16578 2024-01-01 cs.CV 57%

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

Xiawei Li, Qingyuan Xu, Jing Zhang, Tianyi Zhang, Qian Yu, Lu Sheng, Dong Xu

专题命中点云：point cloud(abstract)；分类 cs.CV

2308.11979 2024-01-01 cs.CV 57%

Rotation-Invariant Completion Network

Yu Chen, Pengcheng Shi

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 12 pages, accepted to PRCV 2023 (The 6th Chinese Conference on Pattern Recognition and Computer Vision)

2312.16141 2023-12-27 cs.CV 57%

VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection

Sudip Dhakal, Dominic Carrillo, Deyuan Qu, Michael Nutt, Qing Yang, Song Fu

专题命中点云：point cloud(abstract)；分类 cs.CV

2312.15263 2023-12-27 cs.CV 57%

Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency

Yu Cai, Tianyu Shen, Shi-Sheng Huang, Hua Huang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 13 pages, 7 figures

2309.02139 2023-12-25 cs.CV cs.AI 57%

Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR Data

Mariona Carós, Ariadna Just, Santi Seguí, Jordi Vitrià

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments International conference Machine Vision Applications 2023

2312.13641 2023-12-22 cs.CV 57%

SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection

Yun Zhu, Le Hui, Yaqi Shen, Jin Xie

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by AAAI 2024

2305.03815 2023-12-22 cs.CV 57%

Persistent Homology Meets Object Unity: Object Recognition in Clutter

Ekta U. Samani, Ashis G. Banerjee

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments This work has been accepted for publication in the IEEE Transactions on Robotics

1. 点云 7723 篇

JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues

Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation

Characterizing Perspective Error in Voxel-Based Lidar Scan Matching

SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition

CloSe: A 3D Clothing Segmentation Dataset and Model

Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAM

A Generalized Multi-Modal Fusion Detection Framework

Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals

Unsupervised Pre-Training for 3D Leaf Instance Segmentation

Region-Enhanced Feature Learning for Scene Semantic Segmentation

Registration of algebraic varieties using Riemannian optimization

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion

Minuet: Accelerating 3D Sparse Convolutions on GPUs

Dynamics-aware Adversarial Attack of Adaptive Neural Networks

GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection

Correcting Motion Distortion for LIDAR HD-Map Localization

SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision

Bayesian Heuristics for Robust Spatial Perception

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets

Revisiting Nonlocal Self-Similarity from Continuous Representation

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

Rotation-Invariant Completion Network

VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection

Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency

Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR Data

SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection

Persistent Homology Meets Object Unity: Object Recognition in Clutter