VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion

ArXi:2603.08020v1 Announce Type: new Generating realistic cast shadows for inserted foreground objects is a crucial yet challenging problem in image composition, where maintaining geometric consistency of shadow and object in complex scenes remains difficult due to the ill-posed nature of shadow formation. To address this issue, we propose VSDiffusion, a visibility-constrained two-stage framework designed to narrow the solution space by incorporating visibility priors. In Stage I, we predict a coarse shadow mask to localize plausible shadow generated regions.