PAD3R：从随手拍摄视频中进行位姿感知的动态3D重建
PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos
AI总结：
本文提出PAD3R，利用个性化位姿估计、image-to-3D先验、长期2D点跟踪与可微渲染，从无位姿随手拍单目视频中重建类别无关的高保真可变形3D物体。
摘要：
我们提出了PAD3R，这是一种从随手拍摄、无位姿的单目视频中重建可变形3D物体的方法。与现有方法不同，PAD3R能够处理长视频序列，这些序列包含通常会给传统系统带来挑战的显著物体变形、大规模相机运动和有限视角覆盖。该方法的核心是训练一个个性化、以物体为中心的位姿估计器，并由预训练的image-to-3D模型提供监督。这将引导可变形3D Gaussian表示的优化。该优化还通过在整个输入视频上进行长期2D点跟踪得到正则化。通过结合生成式先验和可微渲染，PAD3R以类别无关的方式重建物体的高保真铰接3D表示。大量定性和定量结果表明，PAD3R具有鲁棒性，并能在各种具有挑战性的场景中良好泛化，凸显了其在动态场景理解和3D内容创作方面的潜力。
英文摘要：
We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale camera movement, and limited view coverage that typically challenge conventional systems. At its core, our approach trains a personalized, object-centric pose estimator, supervised by a pre-trained image-to-3D model. This guides the optimization of deformable 3D Gaussian representation. The optimization is further regularized by long-term 2D point tracking over the entire input video. By combining generative priors and differentiable rendering, PAD3R reconstructs high-fidelity, articulated 3D representations of objects in a category-agnostic way. Extensive qualitative and quantitative results show that PAD3R is robust and generalizes well across challenging scenarios, highlighting its potential for dynamic scene understanding and 3D content creation.
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。
