研究人员推出了一种新颖的三维表面重建模型Surflo，该模型将未加姿态的RGB视图处理成全局潜在状态。这种方法允许通过流匹配解码定向的三维表面点，从而能够通过单次传递从几千到超过一百万个点实现任意输出分辨率。Surflo在与现有前馈方法相比时表现出竞争力，同时比基于优化的技术快得多，提供了全局潜在表示和灵活解码的独特组合。 AI
影响 能够从多个视图灵活高效地进行三维表面重建，可能影响计算机图形学和机器人等领域。
排序理由 该集群描述了一篇关于新颖三维表面重建模型的新学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
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 …
Surflo compresses unposed RGB views into latent tokens and decodes 3D surface points through flow matching, enabling flexible resolution output and efficient processing compared to existing methods.
arXiv:2606.13644v1 Announce Type: new Abstract: 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 point…
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 …