发表机构
Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对可变形3D高斯泼溅中运动监督的域差距问题，提出基于位移流的监督框架，并引入变形-渲染一致性指标，显著提升运动定位与运动-渲染一致性。
AI 中文摘要
准确的动态场景重建对于机器人感知至关重要，其中动态环境的时间一致性表示是必不可少的。可变形3D高斯泼溅（3DGS）通过变形场建模动态场景，近期方法通过将渲染的高斯流与光流对齐来引入运动监督。然而，我们发现这种基于高斯流的监督在运动建模方面仅提供有限的改进。我们识别出该监督范式的一个根本性局限，即渲染高斯流与光流之间存在域差距。为解决此局限，我们提出一种基于位移流的运动监督框架，该框架将每个高斯的3D位移泼溅到图像平面，以提供直接且稳定的优化信号。我们进一步通过中间视图渲染将场景运动与相机运动解耦，从而获得更可靠的运动先验以及对变形和几何的针对性约束。我们还观察到运动保真度与基于图像的评估之间存在差异，即运动感知的提升并不必然转化为更好的渲染图像质量或更高的基于图像的指标分数。受此不匹配的启发，我们引入变形-渲染一致性（DRC），一种衡量预测变形与渲染改进之间对齐程度的运动感知指标。在动态场景基准上的实验显示，运动定位和运动-渲染一致性分别实现了高达39%和6%的显著改进，而基于图像的指标仅变化约0.1%。这些结果证实了运动保真度与基于图像评估之间观察到的差异，证明了DRC在运动感知评估中的重要性。
英文摘要
Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are essential. Deformable 3D Gaussian Splatting (3DGS) models dynamic scenes through deformation fields, and recent methods incorporate motion supervision by aligning rendered Gaussian flow with optical flow. However, we find that such Gaussian-flow-based supervision provides only limited improvements in motion modeling. We identify a fundamental limitation of this supervision paradigm, namely a domain gap between rendered Gaussian flow and optical flow. To address this limitation, we propose a motion supervision framework built on Displacement Flow, which splats per-Gaussian 3D displacements onto the image plane to provide direct and stable optimization signals. We further disentangle scene motion from camera motion via intermediate-view rendering, enabling more reliable motion priors and targeted constraints on deformation and geometry. We also observe a discrepancy between motion fidelity and image-based evaluation, where improved motion awareness does not necessarily translate into better rendered image quality or higher image-based metric scores. Motivated by this mismatch, we introduce Deformation-Rendering Consistency (DRC), a motion-aware metric that measures the alignment between predicted deformation and rendering improvement. Experiments on dynamic scene benchmarks show substantial improvements in motion localization and motion--rendering consistency, reaching up to 39% and 6%, respectively, while image-based metrics change by only about 0.1%. These results confirm the observed mismatch between motion fidelity and image-based evaluation, demonstrating the significance of DRC for motion-aware evaluation.
