Search papers, labs, and topics across Lattice.
FRUC, a novel feed-forward 3D Gaussian splatting framework, addresses dynamic scene reconstruction from uncalibrated collaborative driving views by treating the multi-vehicle network as an unstructured ego-centric multi-camera system. It introduces an ego-centric causal occlusion field to model agent-wise spatio-temporal correlations as latent priors and formulates cross-agent integration as a deterministic residual denoising process. Experiments on V2XReal and UrbanIng-V2X datasets demonstrate that FRUC achieves state-of-the-art performance in rendering quality and efficiency for dynamic collaborative driving environments.
Achieve SOTA 3D scene reconstruction from collaborative driving views without calibration by treating multiple vehicles as a single, unstructured multi-camera system.
We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction frameworks are often hindered by rigid prerequisites, demanding precise spatial calibration and slow per-scene optimization. In this paper, we rethink this task by conceptualizing a distributed multi-vehicle network as a spatio-temporally unstructured ego-centric multi-camera system, where the core challenge lies in enhancing ego-centric occluded geometry through collaboration without degrading the ego's accurately observed visible geometry, while preserving reconstruction efficiency. For efficient reconstruction, FRUC is built upon a visual grounded geometric Transformer backbone to enable one-shot, calibration-free inference from a flexible number of multi-vehicle views. To achieve non-destructive geometric supplementation under uncalibrated cross-agent misalignment, FRUC first introduces an ego-centric causal occlusion field that explicitly derives occlusion evolution as latent priors by modeling agent-wise spatio-temporal correlations. Guided by these occlusion priors, it further formulates cross-agent integration as a deterministic residual denoising process via zero-initialized injection, turning challenging cross-agent fusion into bounded residual learning for robust collaborative blind-spot completion. Through extensive evaluations on the real-world V2XReal and UrbanIng-V2X datasets, FRUC is shown to be a new state-of-the-art for the scene reconstruction of dynamic collaborative driving environments, significantly outperforming existing methods in both rendering quality and efficiency.
