DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
About
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, high-quality material properties, and lighting conditions--that are often impractical to obtain in real-world scenarios. Therefore, we introduce DiffusionRenderer, a neural approach that addresses the dual problem of inverse and forward rendering within a holistic framework. Leveraging powerful video diffusion model priors, the inverse rendering model accurately estimates G-buffers from real-world videos, providing an interface for image editing tasks, and training data for the rendering model. Conversely, our rendering model generates photorealistic images from G-buffers without explicit light transport simulation. Experiments demonstrate that DiffusionRenderer effectively approximates inverse and forwards rendering, consistently outperforming the state-of-the-art. Our model enables practical applications from a single video input--including relighting, material editing, and realistic object insertion.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image-to-image relighting | MIIW cross-scene (test) | RMSE (raw)0.399 | 9 | |
| Forward Rendering | SyntheticScenes | PSNR26 | 8 | |
| Forward Rendering | SyntheticObjects | PSNR28.7 | 8 | |
| Albedo Estimation | InteriorVerse 91 | PSNR22.4 | 7 | |
| Relighting | SyntheticObjects | PSNR27.5 | 6 | |
| Single-view inverse rendering | Interiorverse (test) | Albedo PSNR21.9 | 6 | |
| Forward Neural Rendering | Custom Rendering Dataset (30k artist-crafted and 100k synthetic frames) (test) | PSNR23.758 | 6 | |
| Relighting | MIIW | PSNR16.81 | 6 | |
| Inverse Rendering | SyntheticScenes video dataset (test) | Albedo PSNR26 | 5 | |
| Multi-view material consistency estimation | Hypersim (test) | Albedo RMSE0.0826 | 5 |