MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
This addresses the challenge of real-time dynamic scene modeling for applications like view synthesis and 3D tracking, though it builds incrementally on existing Gaussian-based methods.
The paper tackles the problem of synthesizing 4D dynamic novel views from monocular videos, achieving this in one second with competitive performance and orders of magnitude speedups.
We present MoVieS, a novel feed-forward model that synthesizes 4D dynamic novel views from monocular videos in one second. MoVieS represents dynamic 3D scenes using pixel-aligned grids of Gaussian primitives, explicitly supervising their time-varying motion. This allows, for the first time, the unified modeling of appearance, geometry and motion, and enables view synthesis, reconstruction and 3D point tracking within a single learning-based framework. By bridging novel view synthesis with dynamic 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.