Diffusion Renderer
NVIDIAUniversity of TorontoVector InstituteUniversity of Illinois Urbana-Champaign (UIUC)Video editingVideo-to-video3D segmentationOpen weights
Developed by NVIDIA,University of Toronto,Vector Institute,University of Illinois Urbana-Champaign (UIUC) in 2025, Diffusion Renderer is a video editing model with 1100000000.0 parameters with openly available weights.
About Diffusion Renderer
Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D geometry, h
Details
- Provider
- NVIDIA,University of Toronto,Vector Institute,University of Illinois Urbana-Champaign (UIUC)
- Task
- Video editing,Video-to-video,3D segmentation
- Parameters
- 1100000000.0
- Released
- 2025-03-22
- Open weights
- Yes