Hongxuan Ma — accepted AI-conference papers

2025

IoU-Aware Clustering for Anchor Configuration Determination in Efficient Defect Detection

Yuhao Zhao, Hongxuan Ma, Wei Zou, Zhe Liu, Hu Su, Song Liu

IROS 2025

Deep-learning-based object detection has gained widespread application in surface defect inspection, with anchor-based detectors achieving remarkable success by utilizing dense anchors to align with defects. Determining the optimal anchor configuration, i.e., sizes and aspect ratios of anchor boxes,

Cited by 0 Source ↗Scholar ↗

2025

Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion

Jiangyuan Liu, Hongxuan Ma, Yuxin Guo, Yuhao Zhao, Chi Zhang, Wei Sui +1

ICRA 2025

Transparent object perception is indispensable for numerous robotic tasks. However, accurately segmenting and estimating the depth of transparent objects remain challenging due to complex optical properties. Existing methods primarily delve into only one task using extra inputs or specialized sensor

Cited by 8 Source ↗code ↗Scholar ↗