arXiv：cs.AI· Hui Shan, Keyang Luo, Binjia Zhou, Ming Li, Kai Li, Xin Wang, Zhenyang Li, Zesong Yang, Weikai Chen, Runze Zhang, Xin Wang, Yanwei Fu, Zhen Chen, Xiangru Huang·· 6 小时前
Unravel：从单张图像还原可交互 3D 场景
Unravel: Recovering an Interactive 3D Scene from a Single Image
AI 导读
Unravel 是一个无需训练的框架，能把单张图像转成可交互 3D 场景，其中每个物体都是独立可移动的资产。它先用视觉语言模型规划完全可见的物体、由图像编辑器移除并修复被遮挡区域，再按逆序重建场景，并以点云作为空间关系恢复的主要模态。在多种室内场景实验中，Unravel 比现有方法恢复出更多物体、摆放更忠实，场景也更符合物理合理性。
正文
Authors:Hui Shan, Keyang Luo, Binjia Zhou, Ming Li, Kai Li, Xin Wang, Zhenyang Li, Zesong Yang, Weikai Chen, Runze Zhang, Xin Wang, Yanwei Fu, Zhen Chen, Xiangru Huang
Abstract:We present Unravel, a training-free framework that turns a single image into an interactive 3D scene, where every object is an independent and movable asset. Existing generators either produce one entangled geometry in which no object can be moved, or predict all objects in one feed-forward pass, where a wrong guess cannot be detected or repaired. Unravel instead takes a different approach: it first takes the scene apart, and then puts it back together. Starting from the input image, an agentic harness that iteratively peels the image layer by layer, and adopts point cloud as major modality for spatial relationship recovery. Specifically, a vision-language model plans which objects are fully visible, an image editor removes them and restores the occluded regions. Every edit is verified before being incorporated into the reconstruction. This process gradually turns occluded parts of the scene into direct observation, allowing objects to be reconstructed when they are best exposed rather than hallucinated from the original image alone. The scene is then rebuilt in reverse removal order, so that the supporting objects are naturally placed before the objects they support. Since a single-view image only reveals part of an object, we treat the observed points as a lower bound on its size: an asset may grow to cover its points, but can not shrink away from them. Finally, we physically settle the reconstructed scene to remove floating objects and interpenetrations, followed by an agentic audit that corrects remaining placement errors. Extensive experiments on diverse indoor scenes show that Unravel recovers more objects, places them more faithfully, and produces scenes that are more physically-plausible than existing methods.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16146 [cs.CV] |
| (or arXiv:2610.16146v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16146 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hui Shan [view email]
[v1]
Mon, 12 Oct 2026 04:08:17 UTC (35,429 KB)
来源：arXiv：cs.AI · arxiv.org