发表机构
Graduate School of FSE, Waseda University; Sharp Corporation（早稻田大学FSE研究生院; 夏普公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出仿射对齐图集规范高斯表示，通过逐帧仿射变换吸收全局运动，减少规范与帧间差距，可低成本集成于现有方法，提升大相机运动视频的重建质量。
AI 中文摘要
高斯溅射因其显式结构和快速渲染能力，近期已成为图像和视频的一种高效表示方法。现有的基于高斯的视频表示通常将视频分解为规范高斯和时间变形。然而，当视频包含如相机运动等大规模全局运动时，规范表示可能与各个帧错位，增加了时间变形模型的负担。在本文中，我们提出了一种仿射图集规范高斯表示，在更大的仿射对齐图集空间中构建规范高斯。逐帧仿射变换在规范高斯构建之前吸收全局运动，减少了规范表示与目标帧之间的差距。由于所提方法仅修改规范构建阶段，它可以以可忽略的额外参数成本集成到现有的基于规范高斯的方法中。实验表明，我们的方法尤其改善了具有大相机运动序列的重建质量。
英文摘要
Gaussian splatting has recently emerged as an efficient representation for images and videos due to its explicit structure and fast rendering capability. Existing Gaussian-based video representations often decompose a video into canonical Gaussians and temporal deformation. However, when a video contains large global motion such as camera movement, the canonical representation may become misaligned with individual frames, increasing the burden on the temporal deformation model. In this paper, we propose an affine-atlas canonical Gaussian representation, which constructs canonical Gaussians in a larger affine-aligned atlas space. Frame-wise affine transforms absorb global motion before canonical Gaussian construction, reducing the gap between the canonical representation and target frames. Since the proposed method only modifies the canonical construction stage, it can be integrated into existing canonical-Gaussian-based methods with negligible additional parameter cost. Experiments show that our method improves reconstruction quality especially for sequences with large camera motion.
