Relit-LiVE: Relight Video by Jointly Learning Environment Video

ArXi:2605.06658v1 Announce Type: new Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate intrinsic decomposition, which remains highly unreliable for real-world videos and often leads to distorted appearances, broken materials, and accumulated temporal artifacts during relighting.