PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

  • 类型:arxiv
  • 标识:2609.17521
  • 链接:https://arxiv.org/abs/2609.17521
  • 主分类:multimodal
  • 形态:position
  • 被引:2
  • 被引来源:Semantic Scholar
  • S2被引:2
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:PhysStream is an autoregressive model for physics-grounded image-to-video synthesis that incorporates structured scene memory and supports fine-grained motion control via sparse velocity-increment signals that encode physical quantities, letting the model learn the underlying dynamics.
  • OpenAlex ID:W7213412111
  • OpenAlex DOI:10.48550/arxiv.2609.17521
  • DOI:10.48550/arxiv.2609.17521
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2609.17521
  • OpenAlex更新:2026-09-18
  • 待LLM分类:否
  • 标题中文:PhysStream:基于结构化场景记忆与细粒度运动控制的流式物理约束视频生成
  • TLDR中文:PhysStream 是一个用于物理驱动图像到视频合成的自回归模型,通过引入结构化场景记忆并支持基于稀疏速度增量信号的细粒度运动控制(编码物理量),使模型能够学习底层动力学。
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]