用全局隐状态实现任意分辨率3D表面重建，速度快且一致。
Surflo: Consistent 3D Surface Flow Model with Global State
- 用流动匹配将多视角图像压缩为全局隐状态，解码任意数量3D点。
- 单次前向传播支持从几千到百万级点输出，速度比优化方法快10倍。
- 推理时注入光度梯度，解决点间不一致问题，适合高精度重建场景。
几何结构与视角无关，因此多视角图像对单一3D状态是冗余编码。现有前馈重建模型未能充分利用此特性：局部视图方法生成重叠且未对齐的点云，点数随输入线性增长；全局隐变量方法则受限于固定低分辨率输出。本文提出Surflo，将任意数量无姿态的RGB视图压缩为K个隐状态令牌——一个全局状态，并通过流动匹配独立将噪声点运输至表面，解码出有方向的3D表面点。该方法摆脱了固定网格或令牌预算的限制：相同隐状态可在一次前向传播中生成数千至百万级点。为抑制独立解码带来的局部不一致性，推理时引入光度梯度作为引导项，在微分方程积分过程中关联邻近点。Surflo在表面指标上达到或超越前馈基线，运行速度比需数百张图的优化方法快一个数量级，是首个结合全局隐状态与任意分辨率解码的前馈方法。
原文摘要 · Abstract (English)
Geometry is invariant to viewpoint, which makes any collection of images a redundant encoding of a single 3D state. Existing feed-forward reconstruction models fail to exploit this: per-view methods emit overlapping, unaligned pointmaps that grow linearly with input count, while global-latent methods commit to a fixed, low-resolution output. We introduce Surflo, which compresses a variable number of unposed RGB views into K latent tokens-one global state-and decodes oriented 3D surface points by independently transporting them from noise onto the surface via flow matching. This frees the output from any fixed grid or token budget: the same latent yields from a few thousand to a million points in a single forward pass. To suppress the local inconsistencies inherent to independent per-point decoding, an inference-time guidance term correlates nearby points by injecting a photometric gradient during ODE integration. Surflo matches or surpasses feed-forward baselines on surface metrics, runs an order of magnitude faster than optimization-based methods that require hundreds of views, and is the only feed-forward approach to combine a global latent with arbitrary-resolution decoding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。