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
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This work replaces the static critic with a feed-forward 4D reconstruction reward that explicitly models scene dynamics, allowing coherent motion to receive high consistency rewards, and adds a motion prior that rewards natural scene-flow magnitude while penalizing jitter and non-rigid artifacts.
  • OpenAlex ID:W7203947880
  • OpenAlex DOI:10.48550/arxiv.2608.19556
  • DOI:10.48550/arxiv.2608.19556
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2608.19556
  • OpenAlex更新:2026-09-01
  • 待LLM分类:否
  • 标题中文:Stream4D:面向流式自回归扩散视频模型的 4D 一致性
  • TLDR中文:本文用前馈 4D 重建奖励替代静态 critic,显式建模场景动态,使连贯运动获得高一致性奖励,并加入对自然 scene-flow 幅值进行奖励同时抑制抖动与非刚性伪影的运动先验。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]