4D Human-Scene Reconstruction from Low-Overlap Captures

  • 类型:arxiv
  • 标识:2607.09125
  • 链接:https://arxiv.org/abs/2607.09125
  • 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:StudioRecon is proposed, a pipeline that reconstructs 4D human scenes from sparse, low-overlap cameras by decoupling background and humans by synthesizing hundreds of camera-controlled novel views with a video diffusion model and achieves state-of-the-art novel view synthesis across four real-world datasets.
  • OpenAlex ID:W7168144933
  • OpenAlex DOI:10.48550/arxiv.2607.09125
  • DOI:10.48550/arxiv.2607.09125
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.09125
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:低重叠度采集下的 4D 人体场景重建
  • TLDR中文:提出 StudioRecon,一种通过解耦背景与人体、并利用视频扩散模型合成数百个相机可控新视角,从稀疏低重叠相机重建 4D 人体场景的流水线,在四个真实数据集上达到了 SOTA 的新视角合成效果
  • 来源文件
  • /inbox/tom/_candidates/2026-07-14-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]