AI RESEARCH
CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement
arXiv CS.CV
•
ArXi:2604.18032v1 Announce Type: new Traditional shadow removal networks often treat image restoration as an unconstrained mapping, lacking the physical interpretability required to balance localized texture recovery with global illumination consistency. To address this, we propose CFSR, a multi-modal prior-driven framework that reframes shadow removal as a physics-constrained restoration process. By seamlessly integrating 3D geometric cues with large-scale foundation model semantics, CFSR effectively bridges the 2D-3D domain gap.