Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
It addresses the problem of 4D reconstruction in challenging off-road autonomous driving scenarios, where existing feedforward methods fail due to high-frequency geometry and non-rigid dynamics.
Ground4D introduces a spatially-grounded feedforward 4D reconstruction framework for unstructured off-road scenes, achieving superior reconstruction quality over existing methods on ORAD-3D and RELLIS-3D datasets, with zero-shot generalization to unseen domains.
Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter, and increased non-rigid dynamics. These factors introduce conflicting Gaussian observations across timestamps, leading to either over-smoothed renderings or structural artifacts. To address this issue, we propose Ground4D, a spatially-grounded 4D feedforward framework for pose-free off-road reconstruction. The key idea is to resolve temporal conflicts through spatially localized conditioning. Specifically, we introduce voxel-grounded temporal Gaussian aggregation, which partitions the canonical Gaussian space into spatial voxels and performs query-conditioned temporal attention within each voxel. Intra-voxel softmax normalization ensures that temporal selectivity and spatial occupancy become mutually reinforcing rather than conflicting. We furthermore introduce surface normal cues as auxiliary geometric guidance to regularize the geometry of Gaussian primitives. Extensive experiments on ORAD-3D and RELLIS-3D demonstrate that Ground4D consistently outperforms existing feedforward methods in reconstruction quality and generalizes zero-shot to unseen off-road domains. Project page and code:https://github.com/wsnbws/Ground4D.