Surflo (NeurIPS 2026 Oral) turns a handful of unposed photos into 3D surfaces, 10x faster
rsasaki0109 · x · 2026-09-29
Surflo, a NeurIPS 2026 Oral paper from Kyoto University, UC Berkeley, Kyutai and others, is now open-sourced. It converts 2-80 unposed RGB views into a clean 3D mesh via a fixed-size latent and flow matching, beating pointmap feed-forward models in quality while running an order of magnitude faster than optimization-based methods like Gaussian Wrapping. Code, weights and data released.
Related event: Surflo reconstructs 3D surfaces from few photos, hits NeurIPS 2026 Oral(2 posts)→
More from Multimodal
- Prompt Template: Duotone Cosmic Vision for Striking Two-Color Space Imagery — LudovicCreator · 2026-09-29
- One reference, a hundred styles: Recraft V4 Style demo with prompts — OVolosin82152 · 2026-09-29
- Kling 4.0 full version shows off native 30s clips, cinematic 21:9 in short film — hq4ai · 2026-09-29
- 300M-param image model trained for €5000 claims SD 1.5-level performance — incorporo · 2026-09-29
- Kling 4.0's long-sequence consistency makes it feel like a real filmmaking tool — SimplyAnnisa · 2026-09-29
- Finegrain Agentic Camera Demos Blazing Speed vs ChatGPT Image Processing — mattturck · 2026-09-29