{"ID":5936931,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-13T22:23:12.658881851Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05376","arxiv_id":"2607.05376","title":"MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing","abstract":"Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffusion model by introducing a 4D geometric bridge between sequentially generated views. Our key insight is that an autoregressive 3D reconstruction model naturally interfaces between autoregressively generated views. Given a completed source view, we reconstruct its 3D structure and render a geometric prior of the next target viewpoint, which the diffusion model refines into a high-quality video. To extend generation beyond the teacher's fixed temporal window, we introduce a joint denoising regime where both view slots are initialized from noise during training, enabling temporally unbounded generation. We distill the model via Distribution Matching Distillation with Spatio-Temporal Self-Forcing, closing the train-inference exposure bias gap for both temporal and view-sequential autoregression. Extensive experiments on both synthetic and real-world data demonstrate that MV-Forcing produces geometrically consistent multi-view videos of dynamic scenes at arbitrary lengths and viewpoint counts using a single few-step student model.","short_abstract":"Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a fram...","url_abs":"https://arxiv.org/abs/2607.05376","url_pdf":"https://arxiv.org/pdf/2607.05376v1","authors":"[\"Gal Fiebelman\",\"Hadar Averbuch-Elor\",\"Sagie Benaim\"]","published":"2026-07-06T17:54:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\"]","methods":"[\"Diffusion Model\"]","has_code":false}