Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection
Jiangyi Wang, Na Zhao
Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments.…
cs.CV2024
On-the-fly Point Feature Representation for Point Clouds Analysis
Jiangyi Wang, Zhongyao Cheng, Na Zhao +2
Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution o…
cs.CV2024
Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation
Huizhou Chen, Jiangyi Wang, Yuxin Li +3
3D environment recognition is essential for autonomous driving systems, as autonomous vehicles require a comprehensive understanding of surrounding scenes. Recently, the predominan…