ReSplat: Learning Recurrent Gaussian Splatting accepted to ECCV 2026 Oral
rsasaki0109 · x · 2026-08-16
ReSplat is a feed-forward recurrent model for 3D Gaussian Splatting that iteratively refines Gaussians using rendering error as a gradient-free feedback signal for test-time adaptation. Key features include compact initialization, predicting Gaussians in a subsampled space (16× fewer than per-pixel methods), and recurrent refinement via a weight-sharing module that updates parameters based on rendering errors.
More from Multimodal
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- Open-source anatomy-reveal skill turns Claude into an exploded-view motion design studio — msharmas · 2026-10-16
- Flux 3 Klein vs Flux 2 Klein hands-on: the new base model 'barely usable' for T2I — Both-Rub5248 · 2026-10-16
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- 800,000 Gaussian splats run in WebGPU; Casado sees near-infinite scaling — generativist · 2026-10-16
- Nano Banana 2.1 image generation now live in Perplexity Computer for all users — ChrisUniverse · 2026-10-16