4DGS360：基于单视频动态物体的360°高斯重建

摘要

我们提出4DGS360，一种无需扩散的框架，用于从单目手持视频实现360°动态物体重建。现有方法因过度依赖二维先验，导致初始点过度拟合每个训练视角中的可见表面，难以重建一致的360°几何结构。4DGS360通过先进的3D原生初始化策略应对这一挑战，有效缓解被遮挡区域的几何模糊性问题。我们提出的3D跟踪器AnchorTAP3D利用高置信度的2D跟踪点作为锚点，生成强化的3D点轨迹，抑制漂移现象并提供能保持被遮挡区域几何特征的可靠初始化。这种初始化与优化过程相结合，最终产生连贯的360°四维重建结果。我们还推出了iPhone360基准数据集，其测试相机与训练视角最大间隔达135°，能够实现现有数据集无法支持的360°全方位评估。实验表明，4DGS360在iPhone360、iPhone和DAVIS数据集上均取得定性与定量层面的最优性能。

English

We introduce 4DGS360, a diffusion-free framework for 360^{circ} dynamic object reconstruction from casual monocular video. Existing methods often fail to reconstruct consistent 360^{circ} geometry, as their heavy reliance on 2D-native priors causes initial points to overfit to visible surface in each training view. 4DGS360 addresses this challenge through a advanced 3D-native initialization that mitigates the geometric ambiguity of occluded regions. Our proposed 3D tracker, AnchorTAP3D, produces reinforced 3D point trajectories by leveraging confident 2D track points as anchors, suppressing drift and providing reliable initialization that preserves geometry in occluded regions. This initialization, combined with optimization, yields coherent 360^{circ} 4D reconstructions. We further present iPhone360, a new benchmark where test cameras are placed up to 135^{circ} apart from training views, enabling 360^{circ} evaluation that existing datasets cannot provide. Experiments show that 4DGS360 achieves state-of-the-art performance on the iPhone360, iPhone, and DAVIS datasets, both qualitatively and quantitatively.

4DGS360：基于单视频动态物体的360°高斯重建

4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video

摘要

Support