Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing solutions either rely on image or video generative models distilled to 3D space, harming the geometric coherence and restricting the rendering to training views, or are limited to small-scale 3D scene or object-centric generation. In this work, we propose a 3D generative framework based on Σ-Voxfield grid, a discrete representation where each occupied voxel stores a fixed number of colorized surface samples. To generate this representation, we train a semantic-conditioned diffusion model that operates on local voxel neighborhoods and uses 3D positional encodings to capture spatial structure. We scale to large scenes via progressive spatial outpainting over overlapping regions. Finally, we render the generated Σ-Voxfield grid with a deferred rendering module to obtain photorealistic images, enabling large-scale multiview-consistent 3D scene generation without per-scene optimization. Extensive experiments show that our approach can generate diverse large-scale urban outdoor scenes, renderable into photorealistic images with various sensor configurations and camera trajectories while maintaining moderate computation cost compared to existing approaches.
@article{arxiv.2604.06113,
title = {SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation},
author = {Hiba Dahmani and Nathan Piasco and Moussab Bennehar and Luis Roldão and Dzmitry Tsishkou and Laurent Caraffa and Jean-Philippe Tarel and Roland Brémond},
journal= {arXiv preprint arXiv:2604.06113},
year = {2026}
}