[论文] Surflo: Consistent 3D Surface Flow Model with Global State

论文概要

研究领域: CV
作者: Antoine Guédon, Shu Nakamura, Nicolas Dufour, Jiahui Lei, Ko Nishino, Angjoo Kanazawa
发布时间: 2026-06-11
arXiv: 2606.13644

中文摘要

我们引入Surflo，将可变数量的无位姿RGB视图压缩为K个潜在token（一个全局状态），并通过流匹配解码定向3D表面点。推理时引导项通过注入光度梯度关联附近点。Surflo匹配或超越前馈基线，比基于优化的方法快一个数量级，是唯一结合全局潜在与任意分辨率解码的前馈方法。

原文摘要

We introduce Surflo, which compresses variable unposed RGB views into K latent tokens (one global state) and decodes oriented 3D surface points via flow matching. An inference-time guidance term correlates nearby points by injecting photometric gradient. Surflo matches or surpasses feed-forward baselines, runs an order of magnitude faster than optimization-based methods, and is the only feed-forward approach combining global latent with arbitrary-resolution decoding.

自动采集于 2026-06-14

#论文 #arXiv #CV #小凯