Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving

Researchers posting arXiv paper 2611.07081v1 introduced Wide-View Gaussian Splatting (WV-GS), a feed-forward Gaussian-splatting framework that synthesizes a geometrically consistent wide view from multiple perspective cameras in autonomous driving without per-scene optimization. WV-GS adds Piecewise Perspective Rendering (PPR) to reduce peripheral stretching via local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling (SAPM) to handle camera-dependent photometric variation during training. The authors also released WideDrive, a synthetic benchmark with dense ground-truth wide views, and adapted a LiDAR-projected sparse-reference protocol to real-world datasets; dataset and code are to be publicly released.

arXiv:2611.07081v1 Announce Type: new Abstract: Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unified wide view from spatially separated observations. In this work, we formulate wide view synthesis WVS , which aims to synthesize a geometrically consistent wide view at a specified virtual viewpoint from multiple perspective cameras. Unlike conventional image stitching, WVS requires reasoning about 3D geometry and visibility to handle depth-dependent parallax and occlusions arising from spatially separated camera centers. While vanilla 3D Gaussian Splatting 3DGS enables high-fidelity view synthesis, its reliance on per-scene optimization limits its applicability to driving scenes. Furthermore, WVS introduces additional challenges, e.g. , peripheral stretching under perspective projection and photometric inconsistencies across cameras. To address these challenges, we propose Wide-View Gaussian Splatting WV-GS , a feed-forward Gaussian-splatting framework that synthesizes wide views without per-scene optimization. Specifically, we introduce Piecewise Perspective Rendering PPR to mitigate peripheral stretching through local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling SAPM to account for camera-dependent photometric variations during training. We further introduce WideDrive , a synthetic benchmark providing dense ground-truth wide views and adapt a LiDAR-projected sparse-reference protocol to real-world datasets. Extensive experiments on multiple datasets demonstrate the effectiveness of WV-GS for WVS. Dataset and code will be publicly released.