[2510.24718] Generative View Stitching

Computer Science > Computer Vision and Pattern Recognition arXiv:2510.24718 (cs) [Submitted on 28 Oct 2025 (v1), last revised 9 Apr 2026 (this version, v3)] Title:Generative View Stitching Authors:Chonghyuk Song, Michal Stary, Boyuan Chen, George Kopanas, Vincent Sitzmann View a PDF of the paper titled Generative View Stitching, by Chonghyuk Song and 4 other authors View PDF HTML (experimental) Abstract:Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a predefined camera trajectory, this limitation leads to collisions with the generated scene, after which autoregression quickly collapses. To address this, we propose Generative View Stitching (GVS), which samples the entire sequence in parallel such that the generated scene is faithful to every part of the predefined camera trajectory. Our main contribution is a sampling algorithm that extends prior work on diffusion stitching for robot planning to video generation. While such stitching methods usually require a specially trained model, GVS is compatible with any off-the-shelf video model trained with Diffusion Forcing, a prevalent sequence diffusion framework that we show already provides the affordances necessary for stitching. We then introduce Omni Guidance, a technique that enhances the temporal consistency in stitching by conditioni...