arXiv · 2611.19857
PanDWM: Panoramic 4D Driving World Models
Abstract
Driving world models usually generate videos from six pinhole cameras with separate optical centres and small overlaps, and must learn to keep these views consistent. We present PanDWM, which stitches them into one $360^\circ$ panoramic band. Camera boundaries then fall inside one image, so keeping the views consistent means keeping the image continuous, and each pixel still records its camera ray. Conditioned on layouts, a causal student generates the band window by window in four steps; it is distilled from a causal teacher and trained on its own rollouts. A feed-forward decoder lifts each frame along these rays into 3D Gaussians, and static Gaussians from neighbouring frames complete them into 4D scenes. On nuScenes, scored in one stitched $360^\circ$ view, PanDWM has lower FID and FVD than the multi-camera baselines at $8$-$46\times$ their speed, and keeps its 50-step teacher's FID while lowering FVD by 22-25%.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Jiajun Sun, Zeyu Zhang, Zeyu Ren, Guangfeng Jiang, Yang Zhao, Hao Tang. 2026-11-15. PanDWM: Panoramic 4D Driving World Models. https://searcharxiv.com/abs/2611.19857
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.