发表机构
Tsinghua University; The University of Texas at Dallas; University of Electronic Science and Technology of China（清华大学; 德克萨斯大学达拉斯分校; 电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MVFusion-GS，通过运动方差引导细化与MotionFormer时间注意力模块增强变形网络，显式建模运动强度与时间一致性，在动态场景重建和无干扰重建任务中达到最先进性能。
AI 中文摘要
3D高斯泼溅（3DGS）实现了静态场景的实时新视角合成。通过变形场将其扩展到动态场景最近引起了广泛关注，特别是对于动态场景重建和无干扰重建。然而，现有的变形网络缺乏显式的运动感知：它们既不能捕捉长期运动强度，也不能利用短期时间一致性，导致前景变形不准确和背景中的伪静态残差。我们提出MVFusion-GS，一种用两种互补的运动感知机制增强变形网络的方法。运动方差引导细化聚合每个高斯随时间变化的变形统计量以估计运动方差，并在变形预测期间用于指导动态-静态分离。MotionFormer时间注意力模块在相邻时间步上应用Transformer自注意力以建模局部运动依赖性并提高时间一致性。在动态场景重建和无干扰重建基准上的大量实验证明了最先进的性能，表明显式运动感知改进了前景运动建模和静态背景重建。
英文摘要
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant attention, particularly for dynamic scene reconstructionband distractor-free. However, existing deformation networks lack explicit motion awareness: they neither capture long-term motion intensity nor exploit short-term temporal coherence, leading to inaccurate foreground deformation and pseudo-static residuals in the background. We present MVFusion-GS, a method that enhances deformation networks with two complementary motion-aware mechanisms. The Motion-Variance Guided Refinement aggregates per-Gaussian deformation statistics across time to estimate motion variance and uses it to guide dynamic-static separation during deformation prediction. The MotionFormer Temporal Attention module applies Transformer self-attention over neighboring timesteps to model local motion dependencies and improve temporal consistency. Extensive experiments on both dynamic scene reconstruction and distractor-free reconstruction benchmarks demonstrate state-of-the-art performance, showing that explicit motion awareness improves both foreground motion modeling and static background reconstruction.
