arXiv 2604.043312026-04-06cs.CVcs.AI

GA-GS：基于生成的高斯点散射用于静态场景重建

GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）；The Chinese University of Hong Kong（香港中文大学）；Institute of Advanced Technology, University of Science and Technology of China（中国科学技术大学先进技术研究院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；School of information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）

Yedong Shen, Shiqi Zhang, Sha Zhang, Yifan Duan, Xinran Zhang, Wenhao Yu, Lu Zhang, Jiajun Deng, Yanyong Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出GA-GS方法，通过生成技术辅助恢复动态物体遮挡区域，引入可学习的真实性标量平衡真实背景与生成区域，利用轨迹匹配数据集验证了其在大规模持久遮挡场景中的优越性能。

摘要：

从单目视频中重建静态3D场景对于虚拟现实和自动驾驶等应用至关重要。当前方法通常依赖背景进行静态场景重建，限制了恢复被动态物体遮挡区域的能力。本文提出GA-GS，一种用于静态场景重建的生成辅助高斯点散射方法。关键创新在于利用生成技术辅助恢复遮挡区域。我们采用运动感知模块分割并移除动态区域，然后使用扩散模型填补遮挡区域，提供伪地面真实监督。为平衡真实背景和生成区域的贡献，我们引入可学习的真实性标量，动态调节高斯点的不透明度，以实现真实性感知的渲染和监督。由于不存在提供视频中动态物体真实场景的现有数据集，我们构建了名为轨迹匹配的数据集，使用固定路径机器人记录每个场景（有/无动态物体），从而实现遮挡区域重建的定量评估。在DAVIS和我们数据集上的大量实验表明，GA-GS在静态场景重建中实现了最先进的性能，尤其是在具有大规模、持久遮挡的挑战性场景中。

英文摘要：

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic objects. In this paper, we propose GA-GS, a Generation-Assisted Gaussian Splatting method for Static Scene Reconstruction. The key innovation of our work lies in leveraging generation to assist in reconstructing occluded regions. We employ a motion-aware module to segment and remove dynamic regions, and thenuse a diffusion model to inpaint the occluded areas, providing pseudo-ground-truth supervision. To balance contributions from real background and generated region, we introduce a learnable authenticity scalar for each Gaussian primitive, which dynamically modulates opacity during splatting for authenticity-aware rendering and supervision. Since no existing dataset provides ground-truth static scene of video with dynamic objects, we construct a dataset named Trajectory-Match, using a fixed-path robot to record each scene with/without dynamic objects, enabling quantitative evaluation in reconstruction of occluded regions. Extensive experiments on both the DAVIS and our dataset show that GA-GS achieves state-of-the-art performance in static scene reconstruction, especially in challenging scenarios with large-scale, persistent occlusions.

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。