The v0.1.0 release is a compact toy scaffold. This issue tracks replacing the placeholder module with a closer implementation of: Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Expected work:
- map paper equations or architecture blocks to code
- keep tensor shapes documented
- add a smoke test
- update README without claiming reproduced benchmarks
The v0.1.0 release is a compact toy scaffold. This issue tracks replacing the placeholder module with a closer implementation of: Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Expected work: