LumiTokens: 3D Relighting via Token-Space Lighting Transformation
qixing_huang · x · 2026-08-31
This ECCV 2026 paper introduces LumiTokens, a framework that formulates 3D relighting as a direct transformation on latent scene tokens, bypassing the need for explicit geometry, material decomposition, or rendering equations. Key features include:
- Scene Token Editor: Processes scene and light-ray tokens via self-attention to output updated tokens decodable into multi-view-consistent images.
- Progressive Relighting: Allows incremental lighting additions (environment, point, area lights) that compose directly in token space without re-encoding.
The method achieves competitive quality with sparse views and avoids per-scene optimization.
More from Multimodal
- Museum displays AI-generated art with 'No AI Used' disclaimer — Sauers_ · 2026-08-31
- Porting MiniMax H3 FastVideo LoRA to ComfyUI: 3x speedup achieved — Sad_Berry_4621 · 2026-08-31
- Deep Dive: Creating an AI music video with MiniMax H3 workflow — TheDerminator1337 · 2026-08-31
- 3D Gaussian Splatting demo is incredibly fun — bilawalsidhu · 2026-08-31
- Creating a music video with Adobe Firefly and Kling 3.0 — Kyrannio · 2026-08-31
- Grok Imagine impresses with stellar sound design and improved video quality — Kyrannio · 2026-08-31