Enables precise, physically plausible control over light position, color, and intensity in single images without a 3D model.
March 31, 2026
Original Paper
LightMover: Generative Light Movement with Color and Intensity Controls
arXiv · 2603.27209
The Takeaway
Unlike previous tools that only change global brightness, this uses video diffusion priors to correctly render moving shadows and light falloff. It represents a 10x improvement in the ease of controllable relighting for creative and forensic image editing.
From the abstract
We present LightMover, a framework for controllable light manipulation in single images that leverages video diffusion priors to produce physically plausible illumination changes without re-rendering the scene. We formulate light editing as a sequence-to-sequence prediction problem in visual token space: given an image and light-control tokens, the model adjusts light position, color, and intensity together with resulting reflections, shadows, and falloff from a single view. This unified treatme