DynSUP: 基于未标定图像对的动态高斯溅射
DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
AI总结：
针对动态场景、稀疏视角和未知姿态导致3D高斯溅射几何约束不足的问题，提出DynSUP方法，通过目标级双视图束调整和SE(3)场驱动高斯训练，仅用两幅无姿态图像实现动态场景高斯拟合，显著提升新视角合成效果。
摘要：
3D高斯溅射的最新进展已展现出良好结果。现有方法通常假设静态场景和/或具有已知姿态的多幅图像。由于几何约束不足，动态性、稀疏视角和未知姿态显著增加了问题复杂度。为克服这一挑战，我们提出一种仅使用两幅无已知姿态的图像即可在动态环境中拟合高斯的方法。为此，我们引入两项技术贡献：首先，提出目标级双视图束调整，将动态场景分解为分段刚性组件，联合估计相机姿态和动态物体运动；其次，设计SE(3)场驱动的高斯训练方法，通过可学习的逐高斯变换实现细粒度运动建模。我们的方法能生成高保真动态场景新视角合成，同时准确保留时间一致性和物体运动。在合成和真实世界数据集上的实验表明，该方法显著优于针对静态环境、多图像和/或已知姿态场景设计的现有方法。项目页面见https://colin-de.github.io/DynSUP/。
英文摘要：
Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem complexity due to insufficient geometric constraints. To overcome this challenge, we propose a method that can use only two images without prior poses to fit Gaussians in dynamic environments. To achieve this, we introduce two technical contributions. First, we propose an object-level two-view bundle adjustment. This strategy decomposes dynamic scenes into piece-wise rigid components, and jointly estimates the camera pose and motions of dynamic objects. Second, we design an SE(3) field-driven Gaussian training method. It enables fine-grained motion modeling through learnable per-Gaussian transformations. Our method leads to high-fidelity novel view synthesis of dynamic scenes while accurately preserving temporal consistency and object motion. Experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-art approaches designed for the cases of static environments, multiple images, and/or known poses. Our project page is available at https://colin-de.github.io/DynSUP/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
