cs.CVNov 17, 2026

Autoregressive View Model

Authors: Jensen, Zhou, Samuel Rota Bulo, Denis Rozumny, Duncan Zauss, Peter Hedman, Nikhil Keetha, Philip Torr, 

Organizations: Jinghao · Meta · University of Oxford

Abstract

We present the Autoregressive View Model (AVM), which generates a scene as a stream of views without constructing an explicit 3D representation. Through a unified in-context interface, AVM conditions on images or videos to generate short clips along a requested camera path. Visual context grounds reconstruction and interpolation, while a learned prior enables extrapolation into unseen regions. AVM retrieves relevant views from inputs and generated history to form a bounded active context. We fine-tune a pretrained bidirectional video diffusion transformer with flow matching in an N-in-1-out formulation. We then tune a causal model on its own rollouts to improve photorealism, reduce denoising steps, and limit long-horizon drift. We scale training to approximately 8M scenes and video clips. We evaluate generation capacity and scene persistence across benchmarks for camera control, text control, visual quality, dynamics, sparse and 4D reconstruction, and long-horizon consistency. The results demonstrate that AVM adapts to diverse input and output settings through one in-context interface.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation

    Oct 27, 2026Kaihua Chen, Yiming Gong, Deva Ramanan +1Camera-Controlled Video GenerationLong-Horizon Video Generation

  2. Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context

    Feb 25, 2026JiaKui Hu, Jialun Liu, Liying Yang +73D-Aware Video GenerationCamera-Controlled Video Generation

  3. World in World: Explore the World with World Models

    Sep 10, 2026Chenxi Song, Yanming Yang, Chi ZhangCamera-Controlled Video GenerationLong-Horizon Video Generation