Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models

  • 类型:arxiv
  • 标识:2608.19556
  • 链接:https://arxiv.org/abs/2608.19556
  • 主分类:multimodal
  • 形态:method
  • TLDR:Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction. However, a single rigid 3d reconstruction cannot model a dynamic scene, so this critic penalizes genuine object motion as reconstruction error and is maximized by freezing the vi
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json