Learning Based Point

Learning-based point methods leverage machine learning to process and analyze point cloud data, aiming to improve efficiency and robustness in tasks like 3D object recognition, pose estimation, and image registration. Current research focuses on developing novel architectures, such as transformer-based networks and graph neural networks, to enhance feature extraction and matching, particularly in challenging conditions like adverse weather or low-texture scenes. These advancements are significantly impacting various fields, including robotics, autonomous driving, and medical imaging, by enabling more accurate and reliable 3D perception and analysis. The development of robust and generalizable methods, particularly through techniques like federated learning and data augmentation, is a key area of ongoing investigation.

Papers

July 2, 2024

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
Junsung Park, Kyungmin Kim, Hyunjung Shim
Semantic Segmentation Data Augmentation Mid Range LiDAR Semantic Segmentation Model Adverse Weather Lidar Semantic Segmentation LiDAR Measurement Learning Based Point

March 20, 2024

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Junjie Chen, Jiebin Yan, Yuming Fang, Li Niu
Refining Method Support Vector Image Feature Map Category Agnostic Pose Large Scale ImageNet Learning Based Point

November 17, 2023

Exploring Machine Learning Models for Federated Learning: A Review of Approaches, Performance, and Limitations
Elaheh Jafarigol, Theodore Trafalis, Talayeh Razzaghi, Mona Zamankhani
Machine Learning Model Constructive Approach System Performance Fundamental Limitation Privacy Preserving Machine Learning Federated Learning Application Learning Based Point

November 1, 2023

Enhancing Clustering Representations with Positive Proximity and Cluster Dispersion Learning
Abhishek Kumar, Dong-Gyu Lee
Deep Clustering Clustering Friendly Representation Robust Clustering Close Proximity Learning Based Point Instance Level Loss Clustering Benchmark

August 2, 2023

Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network
Shenbagaraj Kannapiran, Nalin Bendapudi, Ming-Yuan Yu, Devarth Parikh, Spring Berman, Ankit Vora, Gaurav Pandey
Neural Network Visual Odometry Feature Matching Visual Simultaneous Localization Point Feature Line Feature Learning Based Point Stereo Visual Odometry

October 22, 2022

Learning Point-Language Hierarchical Alignment for 3D Visual Grounding
Jiaming Chen, Weixin Luo, Ran Song, Xiaolin Wei, Lin Ma, Wei Zhang
Visual Representation Visual Grounding Linguistic Representation Language Alignment Hierarchical Alignment Learning Based Point Japanese Sentence

August 18, 2022

Unifying Visual Perception by Dispersible Points Learning
Jianming Liang, Guanglu Song, Biao Leng, Yu Liu
Visual Task Learning Based Point Universal Visual Perception

July 22, 2022

Learning Generalized Non-Rigid Multimodal Biomedical Image Registration from Generic Point Set Data
Zachary MC Baum, Tamas Ungi, Christopher Schlenger, Yipeng Hu, Dean C Barratt
Medical Image Registration Point Transformer Non Rigid Registration Point Set Learning Based Point Semantic Aware Deformation

Learning Based Point

Papers

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

Exploring Machine Learning Models for Federated Learning: A Review of Approaches, Performance, and Limitations

Enhancing Clustering Representations with Positive Proximity and Cluster Dispersion Learning

Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network

Learning Point-Language Hierarchical Alignment for 3D Visual Grounding

Unifying Visual Perception by Dispersible Points Learning

Learning Generalized Non-Rigid Multimodal Biomedical Image Registration from Generic Point Set Data