LightFuse SOTA Relightable 3D Gaussian Reconstruction Beats Baseline by 9.74dB
janusch_patas · x · 2026-09-01
LightFuse introduces the first framework for relightable multi-scan interactive Gaussian reconstruction with explicit material-illumination decomposition. Using ray-tracing-oriented geometry optimization and staged inverse rendering, it achieves state-of-the-art quality, surpassing the strongest baseline by +9.74 dB PSNR and +0.121 SSIM.
Related event: LightFuse Enables Relightable 3D Gaussian Reconstruction with 9.74dB Gain(2 posts)→
More from Research
- AI Research Preference Models: Using Compute to Decide What Experiments to Run — anirudhg9119 · 2026-09-01
- RPM-guided search sets new SOTA on benchmarks, proving selection scales with compute — anirudhg9119 · 2026-09-01
- Inference-only RPM: Frozen LLM Ranks Candidates to Save Compute — anirudhg9119 · 2026-09-01
- From score forecasting to preference ranking: picking which of 15 ideas to run — anirudhg9119 · 2026-09-01
- AI Research Agents Face Bottleneck: Ideas Outpace GPU Budget — anirudhg9119 · 2026-09-01
- Paper: AI Research Preference Models Solve Compute Bottleneck — anirudhg9119 · 2026-09-01