MoVieS：一秒内完成运动感知的 4D 动态视角合成
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
用像素对齐的高斯原语显式监督时变运动，把外观、几何、运动统一进单一学习框架，使单目视频的 4D 重建、新视角合成与 3D 点跟踪共享同一表示；做动态场景重建或需要从视频直接导出场景流、运动分割的工作可直接复用这一表示与监督方式。
原文依据 represents dynamic 3D scenes with pixel-aligned Gaussian primitives and explicitly supervises their time-varying motions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 MoVieS，一种运动感知的视角合成模型，可在一秒内从单目视频重建 4D 动态场景。该模型以像素对齐的高斯原语表示动态三维场景，并对其随时间变化的运动进行显式监督。这使得首次能够从单目视频中统一建模外观、几何与运动，并在单一基于学习的框架内实现重建、视角合成与 3D 点跟踪。通过将视角合成与几何重建相衔接，MoVieS 得以在多种数据集上进行大规模训练，且对任务特定监督的依赖极小。因此，它也能自然支持一系列零样本应用，例如场景流估计与运动目标分割。大量实验验证了 MoVieS 在多项任务上的有效性与高效性，在取得有竞争力性能的同时带来数个数量级的加速。
英文原文摘要 964 字符
We present MoVieS, a Motion-aware View Synthesis model that reconstructs 4D dynamic scenes from monocular videos in one second. It represents dynamic 3D scenes with pixel-aligned Gaussian primitives and explicitly supervises their time-varying motions. This allows, for the first time, the unified modeling of appearance, geometry and motion from monocular videos, and enables reconstruction, view synthesis and 3D point tracking within a single learning-based framework. By bridging view synthesis with geometry reconstruction, MoVieS enables large-scale training on diverse datasets with minimal dependence on task-specific supervision. As a result, it also naturally supports a wide range of zero-shot applications, such as scene flow estimation and moving object segmentation. Extensive experiments validate the effectiveness and efficiency of MoVieS across multiple tasks, achieving competitive performance while offering several orders of magnitude speedups.