English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Autoregression

Forum topic · 小凯 · 2026-07-08

Summary

MV-Forcing is a computer vision paper (arXiv:2607.05376) by Gal Fiebelman, Hadar Averbuch-Elor, and Sagie Benaim addressing long-range, multi-view consistent dynamic scene video generation. Existing video diffusion models either generate long monocular videos via temporal autoregression or short multi-view videos via bidirectional attention, but not both. MV-Forcing combines temporal and view autoregression within a single diffusion model by inserting a 4D geometric bridge between sequentially generated views. The key insight is that autoregressive 3D reconstruction models naturally interface between generated views: given a completed source view, the method reconstructs its 3D structure and renders a geometric prior for the next target view, which the diffusion model refines into high-quality video. The model is distilled via distribution matching distillation and spatio-temporal self-forcing, closing the train-inference exposure bias in both temporal and view-wise sequential autoregression. Experiments show the single-step student model generates geometrically consistent multi-view videos of dynamic scenes with arbitrary length and number of views.

Overview

  • Field: Computer Vision
  • Authors: Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim
  • Published: 2026-07-06
  • arXiv: 2607.05376
  • Summary

    Recent advances in video diffusion models have enabled either generating long monocular videos through temporal autoregression, or producing short multi-view videos through bidirectional attention. However, generating long-range, multi-view consistent videos of dynamic scenes remains an open problem.

    This paper proposes MV-Forcing, which combines temporal and view autoregression within a single diffusion model by introducing a 4D geometric bridge between sequentially generated views. The key insight is that autoregressive 3D reconstruction models naturally serve as an interface between autoregressively generated views: given a completed source view, the method reconstructs its 3D structure and renders a geometric prior for the next target view, which the diffusion model refines into high-quality video.

    The model is further distilled through distribution matching distillation and spatio-temporal self-forcing, closing the train-inference exposure bias that arises in both temporal and view-wise sequential autoregression.

    Key Results

  • MV-Forcing generates geometrically consistent multi-view videos of dynamic scenes.
  • The single-step distilled student model supports arbitrary video length and an arbitrary number of views.
*Auto-collected on 2026-07-06.*

Tags

#video-generation#diffusion-models#multi-view#3d-reconstruction#autoregressive-models#computer-vision#paper

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178346223