arXiv 2607.004982026-07-02cs.CV

基于部分单目观测的生成式重建鲁棒3D对齐

Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations

School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学与技术学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Engineering and Applied Science, University of Pennsylvania（宾夕法尼亚大学工程与应用科学学院）；School of Tech Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；Independent Researcher（独立研究员）；School of Electronic Engineering and Information Science, University of Science and Technology of China（中国科学技术大学电子工程与信息科学学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Robotics, Wuhan University（武汉大学机器人学院）；Xiaomi EV（小米汽车）

Yuchen Zhang, Luanyuan Dai, Yiwei Wang, Xiwei Xu, Jianing Zhang, Johnny. r. zhang, Xianhui Meng, Yanbiao Ma, Jiayi Ma, Xiaoshuai Hao

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对生成式3D重建与部分单目观测对齐的挑战，提出无训练可解释几何对齐框架，通过Sim(3)变换恢复度量尺度与位姿，引入幻觉滤波抑制异常，在基准测试中显著优于传统和学习方法。

摘要：

将生成式3D重建与部分单目观测对齐是计算机视觉中一个关键但探索不足的挑战。由于噪声、稀疏的单目输入与密集生成先验之间存在严重不对称性，其尺度模糊和几何幻觉，加上缺乏初始重叠，使得传统配准流程失效。为解决这些问题，我们提出一个无需训练且可解释的几何对齐框架，通过3D相似变换（Sim(3)）锚定生成式3D先验，从而恢复准确的度量尺度和位姿。具体而言，我们引入显式尺度因子以解决度量模糊性，并采用粗到细的对齐策略，利用几何感知描述子进行鲁棒初始化，以及解耦闭式求解器进行精度细化。此外，我们引入幻觉滤波操作以有效抑制由幻觉几何引起的异常。为了在这些极端条件下评估对齐性能，我们提出了GenPMOAlign--Where2Place，一个专门为生成式到部分单目观测对齐设计的严格基准。实验表明，我们的方法实现了稳定且准确的配准，显著优于经典几何流程和最新的基于学习的基线。代码和基准将公开发布。

英文摘要：

Aligning generative 3D reconstructions with partial monocular observations is a critical but under-explored challenge in computer vision. This task is inherently ill-posed due to severe asymmetries between noisy, sparse monocular inputs and dense generative priors, whose scale ambiguity and geometric hallucinations, combined with the lack of initial overlap, render traditional registration pipelines ineffective. To resolve these issues, we propose a training-free and interpretable geometric alignment framework that grounds generative 3D priors via a 3D similarity transformation (Sim(3)), which can recover accurate metric scale and pose. Specifically, we introduce an explicit scale factor to resolve metric ambiguity and employ a coarse-to-fine alignment strategy, leveraging geometry-aware descriptors for robust initialization and a decoupled closed-form solver for precision refinement. In addition, we introduce a Hallucination Filtering operation to effectively suppress outliers caused by hallucinated geometry. To evaluate alignment performance under these extreme conditions, we introduce GenPMOAlign--Where2Place, a rigorous benchmark specifically designed for Generative-to-Partial Monocular Observational Alignment. Experiments demonstrate that our method achieves stable and accurate registration, substantially outperforming both classical geometric pipelines and state-of-the-art learning-based baselines. Code and the benchmark will be publicly released.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。