CoGS: 从单目视频中构建组合式动态人-物场景高斯泼溅
CoGS: Compositional Dynamic Human-Object Scenes Gaussian Splatting from Monocular Video
AI总结：
提出CoGS框架，通过组合式高斯泼溅将单目视频分解为人体、刚体物体和静态场景三个分支，并采用六阶段优化实现动态人-物交互场景的忠实重建。
摘要：
从单目视频重建动态人-物交互场景是困难的，因为人体、被操纵物体和背景遵循不同的运动模型，却共享相同的像素。现有的动态辐射场和高斯泼溅方法常常纠缠这些组件，导致物体运动泄露到人体或静态场景中，并且单目人体重建在很少观察到的区域仍然约束不足。我们提出CoGS，一个用于单目人-物场景重建的组合式高斯泼溅框架。CoGS将视频分解为三个协调的分支：从完整规范先验初始化的铰接人体、由估计物体轨迹驱动的刚体物体场、以及当可用时由弱场景平面基元正则化的静态场景场。一个六阶段优化调度首先独立稳定人体和物体，然后在全图像监督、可见性感知人体锚定、物体轮廓和运动约束以及延迟场景正则化下将它们与场景融合。这种设计使每个组件负责自己的几何和运动，同时允许光度证据纠正最终合成。在HOSNeRF和NeuMan上的实验表明，CoGS改进了人-物交互重建和野外人体-场景渲染，在全帧和人体聚焦评估中实现了更强的保真度和感知质量。代码将在发表后发布。
英文摘要：
Reconstructing dynamic human--object interaction scenes from monocular video is difficult because the human, manipulated object, and background obey different motion models while sharing the same pixels. Existing dynamic radiance-field and Gaussian-splatting methods often entangle these components, causing object motion to leak into the human or static scene, and monocular human reconstruction remains underconstrained in regions that are rarely observed. We present CoGS, a compositional Gaussian-splatting framework for monocular human--object scene reconstruction. CoGS decomposes the video into three coordinated branches: an articulated human initialized from a complete canonical prior, a rigid object field driven by an estimated object trajectory, and a static scene field regularized by weak scene-only planar primitives when available. A six-stage optimization schedule first stabilizes the human and object independently, then fuses them with the scene under full-image supervision, visibility-aware human anchoring, object silhouette and motion constraints, and delayed scene regularization. This design keeps each component responsible for its own geometry and motion while allowing photometric evidence to correct the final composite. Experiments on HOSNeRF and NeuMan show that CoGS improves both human--object interaction reconstruction and in-the-wild human--scene rendering, achieving stronger fidelity and perceptual quality across full-frame and human-focused evaluations. Code will be released upon publication.
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。
