为单目视频动态高斯泼溅学习显式连续运动表示
Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
用 SE(3) B 样条运动基显式参数化动态高斯的位置与朝向形变，并自适应调整基与控制点数量，可直接迁移到任何需要连续运动建模的动态辐射场/高斯泼溅管线；多视图扩散模型作为正则化先验缓解对训练视角过拟合的思路也可复用于少视角动态重建。
原文依据 explicitly model continuous position and orientation deformation of dynamic Gaussians, using an SE(3) B-spline motion bases
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一种从单目视频中实现高质量动态高斯泼溅的方法。为此，我们在本工作中较以往方法更进一步，使用带有一组紧凑控制点的 SE(3) B 样条运动基，显式地建模动态高斯的位置与朝向的连续形变。为在提升计算效率的同时增强对复杂运动的建模能力，我们设计了一种自适应控制机制，用于动态调整运动基与控制点的数量。此外，我们提出一种软分段重建策略以缓解长间隔运动干扰，并采用多视图扩散模型提供多视图线索，以避免对训练视角的过拟合。大量实验表明，我们的方法在新视角合成上优于最优方法。代码已公开于 https://github.com/hhhddddddd/se3bsplinegs。
英文原文摘要 925 字符
We present an approach for high-quality dynamic Gaussian Splatting from monocular videos. To this end, we in this work go one step further beyond previous methods to explicitly model continuous position and orientation deformation of dynamic Gaussians, using an SE(3) B-spline motion bases with a compact set of control points. To improve computational efficiency while enhancing the ability to model complex motions, an adaptive control mechanism is devised to dynamically adjust the number of motion bases and control points. Besides, we develop a soft segment reconstruction strategy to mitigate long-interval motion interference, and employ a multi-view diffusion model to provide multi-view cues for avoiding overfitting to training views. Extensive experiments demonstrate that our method outperforms state-of-the-art methods in novel view synthesis. Our code is available at https://github.com/hhhddddddd/se3bsplinegs.