Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
This work addresses the challenge of synthesizing novel views from monocular videos for applications like computer vision and graphics, representing an incremental improvement over prior methods.
The paper tackles the problem of high-quality dynamic Gaussian Splatting from monocular videos by explicitly modeling continuous position and orientation deformation using SE(3) B-spline motion bases, and it outperforms state-of-the-art methods in novel view synthesis as demonstrated in extensive experiments.
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.