Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark

  • 类型:arxiv
  • 标识:2607.29684
  • 链接:https://arxiv.org/abs/2607.29684
  • 主分类:multimodal
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • 影响力被引:0
  • TLDR:This paper offers a new perspective for RGB-NIR low-light imaging by incorporating 3D-aware neural modeling, which obviates the requirement for clean RGB data collection, and generalizes across different noise levels.
  • 待LLM分类:否
  • 标题中文:面向暗光场景的鲁棒且 3D 感知的 RGB-NIR 成像
  • TLDR中文:本文为RGB-NIR低光成像提供新视角:通过引入3D感知神经建模,无需采集干净RGB数据,并能跨不同噪声水平泛化。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-03-agent-rag-longcontext-candidates.json
  • [S2 enrich]