Preprint
Sep 2026
TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation
Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this be...
Song-He Wang, Li-Fu Wei, Shuo-Lin Xu et al.
· 0 citations