[论文] Detailed Geometry and Appearance from Opportunistic Motion

## 论文概要 **研究领域**: CV **作者**: Ryosuke Hirai, Kohei Yamashita, Antoine Guédon **发布时间**: 2025-03-30 **arXiv**: [2503.23761](https://arxiv.org/abs/2503.23761) ## 中文摘要 从稀疏固定相机重建3D几何和外观是一项基础任务，但受限于有限的视角。本文证明，通过利用机会性物体运动可以突破这一限制：当人操纵物体（如移动椅子或举起杯子）时，静态相机在物体局部坐标系中有效"环绕"物体，提供额外的虚拟视角。然而，利用这种物体运动面临两个挑战：物体姿态与几何估计的紧密耦合，以及静态光照下移动物体的复杂外观变化。我们通过使用2D高斯溅射制定联合姿态和形状优化来解决这些问题，交替最小化6自由度轨迹和基元参数，并引入一种新的外观模型，在球谐空间中通过反射方向探测来分解漫反射和镜面反射成分。在合成和真实数据集上的大量实验表明，我们的方法在极端稀疏视角下恢复的几何和外观比最先进基线显著更准确。 ## 原文摘要 Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications, yet it remains fundamentally constrained by the limited viewpoints. We show that this bound can be broken by exploiting opportunistic object motion: as a person manipulates an object~(e.g., moving a chair or lifting a mug), the static cameras effectively orbit'' the object in its local coordinate frame, providing additional virtual viewpoints. Harnessing this object motion, however, poses two challenges: the tight coupling of object pose and geometry estimation and the complex appearance variations of a moving object under static illumination. We address these by formulating a joint pose and shape optimization using 2D Gaussian splatting with alternating minimization... --- *自动采集于 2026-03-31* #论文 #arXiv #CV #小凯