Honglin Sun — accepted AI-conference papers

2025

Complete Corruption-Aware Retinex Framework for Low-Light Image Enhancement

Yifei Zhang, Honglin Sun, Yuyang Gao, Jianan Xie, Kenji Hashimoto

IROS 2025

Retinex theory, which treats an image as a composition of illuminance and reflectance, has made significant progress in low-light image enhancement. Previous methods attempt to refine the impractical Retinex theory by introducing deviations in estimated illumination and reflectance to develop more p

Cited by 0 Source ↗code ↗Scholar ↗

2025

Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception

Lei He, Qiaoyi Wang, Honglin Sun, Qing Xu, Bolin Gao, Shengbo Eben Li +2

IROS 2025

Visual bird’s eye view (BEV) perception, dute to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception still relies on LiDAR data to construct ground truth databa

Cited by 2 Source ↗Scholar ↗