3D 视觉 - arXivDaily 专题

2208.14699 2022-09-01 cs.LG cs.CV 57%

Let us Build Bridges: Understanding and Extending Diffusion Generative Models

Xingchao Liu, Lemeng Wu, Mao Ye, Qiang Liu

专题命中点云：point cloud(abstract)；分类 cs.CV

2203.04007 2022-09-01 cs.CV cs.AI 57%

DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction

Jiajun Fei, Ziyu Zhu, Wenlei Liu, Zhidong Deng, Mingyang Li, Huanjun Deng, Shuo Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 16 pages, accepted by AAAI 2022 (https://ojs.aaai.org/index.php/AAAI/article/view/19939), with technical appendix

2208.13414 2022-08-30 cs.CV 57%

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

Peng Wu, Lipeng Gu, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Gary Cheng, Mingqiang Wei

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 18 pages, 9 figures

2208.10056 2022-08-29 cs.CV 57%

Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking

JunYoung Gwak, Silvio Savarese, Jeannette Bohg

专题命中点云：point cloud(abstract)；分类 cs.CV

2206.08362 2022-08-29 cs.CV 57%

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at ICML2022 Thirty-ninth International Conference on Machine Learning

2202.11287 2022-08-25 cs.CV cs.CR cs.LG 57%

LPF-Defense: 3D Adversarial Defense based on Frequency Analysis

Hanieh Naderi, Kimia Noorbakhsh, Arian Etemadi, Shohreh Kasaei

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 15 pages, 7 figures

2208.08741 2022-08-19 cs.LG cs.AI cs.CV 57%

Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification

Quanshi Zhang, Xu Cheng, Yilan Chen, Zhefan Rao

专题命中点云：point cloud(abstract)；分类 cs.CV

2208.08202 2022-08-18 cs.RO 57%

Elevation State-Space: Surfel-Based Navigation in Uneven Environments for Mobile Robots

Fetullah Atas, Grzegorz Cielniak, Lars Grimstad

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Accepted to IROS 2022

2208.07588 2022-08-17 cs.RO 57%

Human-to-Robot Manipulability Domain Adaptation with Parallel Transport and Manifold-Aware ICP

Anna Reithmeir, Luis Figueredo, Sami Haddadin

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 8 pages, 6 figures, to be published in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2207.13226 2022-08-16 cs.CV 57%

Boosting Point-BERT by Multi-choice Tokens

Kexue Fu, Mingzhi Yuan, Manning Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

2106.13863 2022-08-12 cs.CV cs.LG 57%

Steerable 3D Spherical Neurons

Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ICML2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:15330-15339, 2022. https://proceedings.mlr.press/v162/melnyk22a.html

2208.04766 2022-08-10 cs.CV 57%

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation

Chunyu Sun, Xin Tong, Yang Liu

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by Computational Visual Media. Project page: https://isunchy.github.io/projects/3d_instance_segmentation.html

2208.04043 2022-08-09 cs.CV 57%

SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty

Gwangtak Bae, Byungjun Kim, Seongyong Ahn, Jihong Min, Inwook Shim

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ECCV 2022

2208.03949 2022-08-09 cs.CV 57%

Extrinsic Camera Calibration with Semantic Segmentation

Alexander Tsaregorodtsev, Johannes Müller, Jan Strohbeck, Martin Herrmann, Michael Buchholz, Vasileios Belagiannis

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages, 3 figures, accepted at the 25th International Conference on Intelligent Transportation Systems (ITSC) 2022

2111.09515 2022-08-09 cs.CV 57%

Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Point Density Level Estimation

Yantao Lu, Xuetao Hao, Yilan Li, Weiheng Chai, Shiqi Sun, Senem Velipasalar

专题命中点云：point cloud(abstract)；分类 cs.CV

2208.03141 2022-08-08 cs.CV 57%

TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection

Zhipeng Luo, Gongjie Zhang, Changqing Zhou, Tianrui Liu, Shijian Lu, Liang Pan

专题命中点云：point cloud(abstract)；分类 cs.CV

2208.02792 2022-08-05 cs.RO cs.SY eess.SY 57%

A Cooperative Perception Environment for Traffic Operations and Control

Hanlin Chen, Brian Liu, Xumiao Zhang, Feng Qian, Z. Morley Mao, Yiheng Feng

专题命中点云：point cloud(abstract)；分类 cs.RO

2208.01166 2022-08-03 cs.CV 57%

Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions

Carlos A. Diaz-Ruiz, Youya Xia, Yurong You, Jose Nino, Junan Chen, Josephine Monica, Xiangyu Chen, Katie Luo, Yan Wang, Marc Emond, Wei-Lun Chao, Bharath Hariharan, Kilian Q. Weinberger, Mark Campbell

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by CVPR 2022

2112.03777 2022-08-03 cs.CV cs.LG 57%

Variance-Aware Weight Initialization for Point Convolutional Neural Networks

Pedro Hermosilla, Michael Schelling, Tobias Ritschel, Timo Ropinski

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at ECCV 2022

2106.06882 2022-08-02 cs.CV cs.LG 57%

Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

Kyle Vedder, Eric Eaton

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages, 5 figures. Submitted to IROS 2022. All models, weights, experimental configurations, and datasets used are publicly available at http://vedder.io/sparse_point_pillars

Journal ref International Conference on Intelligent Robots and Systems (IROS) 2022

2004.01643 2022-08-01 cs.CV cs.LG eess.IV 57%

Quantifying Data Augmentation for LiDAR based 3D Object Detection

Martin Hahner, Dengxin Dai, Alexander Liniger, Luc Van Gool

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 2022 Update

2111.13981 2022-07-28 cs.RO 57%

Kilometer-scale autonomous navigation in subarctic forests: challenges and lessons learned

Dominic Baril, Simon-Pierre Deschênes, Olivier Gamache, Maxime Vaidis, Damien LaRocque, Johann Laconte, Vladimír Kubelka, Philippe Giguère, François Pomerleau

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Published in Field Robotics Volume 2. Paper number 50

2107.00228 2022-07-28 cs.LG cs.CV 57%

Scalable Certified Segmentation via Randomized Smoothing

Marc Fischer, Maximilian Baader, Martin Vechev

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ICML'21

2207.12691 2022-07-27 cs.CV 57%

CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving

Hui-Xian Cheng, Xian-Feng Han, Guo-Qiang Xiao

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ICME 2022

2207.12655 2022-07-27 cs.CV 57%

Semi-supervised 3D Object Detection with Proficient Teachers

Junbo Yin, Jin Fang, Dingfu Zhou, Liangjun Zhang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

2206.00214 2022-07-27 cs.CV 57%

LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

Matthew Pitropov, Chengjie Huang, Vahdat Abdelzad, Krzysztof Czarnecki, Steven Waslander

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 4 figures and 5 tables. Accepted in IEEE IV 2022

2207.11753 2022-07-26 cs.CV cs.AI 57%

Label-Guided Auxiliary Training Improves 3D Object Detector

Yaomin Huang, Xinmei Liu, Yichen Zhu, Zhiyuan Xu, Chaomin Shen, Zhengping Che, Guixu Zhang, Yaxin Peng, Feifei Feng, Jian Tang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Yaomin Huang and Xinmei Liu are with equal contribution. This paper has been accepted by ECCV 2022

2205.11925 2022-07-26 cs.CV cs.AI 57%

Robust 3D Object Detection in Cold Weather Conditions

Aldi Piroli, Vinzenz Dallabetta, Marc Walessa, Daniel Meissner, Johannes Kopp, Klaus Dietmayer

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Oral

Journal ref 2022 IEEE Intelligent Vehicles Symposium (IV)

2012.10217 2022-07-26 cs.CV 57%

SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation

An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou

专题命中点云：point cloud(abstract)；分类 cs.CV

Journal ref IEEE Transactions on Image Processing, vol. 31, pp. 4952-4965, 2022

2203.03041 2022-07-25 cs.CV 57%

Highly Accurate Dichotomous Image Segmentation

Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, Luc Van Gool

专题命中点云：3D reconstruction(abstract)；分类 cs.CV

Comments 29 pages, 18 figures, ECCV 2022

1. 点云 7723 篇

Let us Build Bridges: Understanding and Extending Diffusion Generative Models

DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

LPF-Defense: 3D Adversarial Defense based on Frequency Analysis

Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification

Elevation State-Space: Surfel-Based Navigation in Uneven Environments for Mobile Robots

Human-to-Robot Manipulability Domain Adaptation with Parallel Transport and Manifold-Aware ICP

Boosting Point-BERT by Multi-choice Tokens

Steerable 3D Spherical Neurons

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation

SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty

Extrinsic Camera Calibration with Semantic Segmentation

Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Point Density Level Estimation

TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection

A Cooperative Perception Environment for Traffic Operations and Control

Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions

Variance-Aware Weight Initialization for Point Convolutional Neural Networks

Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

Quantifying Data Augmentation for LiDAR based 3D Object Detection

Kilometer-scale autonomous navigation in subarctic forests: challenges and lessons learned

Scalable Certified Segmentation via Randomized Smoothing

CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving

Semi-supervised 3D Object Detection with Proficient Teachers

LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

Label-Guided Auxiliary Training Improves 3D Object Detector

Robust 3D Object Detection in Cold Weather Conditions

SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation

Highly Accurate Dichotomous Image Segmentation