5 papers
PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
Yufei Han, Chu Zhou, Youwei Lyu +6
Accurate reconstruction of reflective surfaces remains a fundamental challenge in computer vision, with broad applications in real-time virtual reality and digital content creation…
Architectural Unification for Polarimetric Imaging Across Multiple Degradations
Chu Zhou, Yufei Han, Junda Liao +6
Polarimetric imaging aims to recover polarimetric parameters, including Total Intensity (TI), Degree of Polarization (DoP), and Angle of Polarization (AoP), from captured polarized…
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Muxi Diao, Lele Yang, Wuxuan Gong +6
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcemen…
PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
Yufei Han, Bowen Tie, Heng Guo +5
Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fas…
RotatedMVPS: Multi-view Photometric Stereo with Rotated Natural Light
Songyun Yang, Yufei Han, Jilong Zhang +4
Multiview photometric stereo (MVPS) seeks to recover high-fidelity surface shapes and reflectances from images captured under varying views and illuminations. However, existing MVP…