用SE(3)样条显式建模动态高斯的连续运动，提升单目视频重建质量。
Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
- 采用SE(3)样条基与控制点显式表示动态高斯的位置和姿态变化
- 自适应调整控制点数量，在保持精度的同时提升计算效率
- 结合软分割重建与多视角扩散模型，减少长距离运动干扰
本文提出一种从单目视频生成高质量动态高斯溅射的方法。不同于以往方法，我们进一步显式建模动态高斯的位置与姿态的连续变形，采用基于SE(3)的B样条运动基函数，仅用少量控制点即可实现精准表达。为兼顾计算效率与复杂运动建模能力，设计了自适应控制机制，动态调节运动基函数与控制点数量。此外，提出软分割重建策略以缓解长间隔运动干扰，并引入多视角扩散模型提供多视角先验，避免对训练视图过拟合。大量实验表明，本方法在新视角合成任务上优于当前最优方法。代码已开源：https://github.com/hhhddddddd/se3bsplinegs。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。