4DGS360: 360{\deg} Gaussian Reconstruction of Dynamic Objects from a Single Video

TL;DR

4DGS360 is a novel framework for reconstructing 360-degree dynamic objects from monocular videos, overcoming geometric ambiguities with advanced 3D initialization and tracking, and demonstrating superior performance on new and existing datasets.

Contribution

The paper introduces 4DGS360, a diffusion-free method with a new 3D-native initialization and AnchorTAP3D tracker for accurate 360-degree dynamic object reconstruction from monocular videos.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively handles occlusions and geometric ambiguities.

Introduces iPhone360 benchmark for 360-degree evaluation.

Abstract

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.