English(EN) RayFormer: Modeling Inter- and Intra-Ray Similarity for NeRF-Based Video Snapshot Compressive Imaging

RayFormer AI模型在视频快照压缩成像领域达到SOTA

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 10:48

研究人员推出RayFormer，一种用于视频快照压缩成像（SCI）的新方法，可提高重建质量。该方法采用一种块级光线采样策略和光线内/光线间Transformer，以更好地捕捉动态场景中的结构相似性。通过建模空间和深度相关性，RayFormer在从单次快照测量中重建场景方面取得了最先进的性能。 AI

影响引入了一种新颖的基于Transformer的方法，用于从单次快照改进视频重建。

排序理由这是一篇详细介绍视频快照压缩成像新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Yubo Dong, Danhua Liu, Anqi Li, Zhenyuan Lin · 2026-05-01 04:00

RayFormer: Modeling Inter- and Intra-Ray Similarity for NeRF-Based Video Snapshot Compressive Imaging

arXiv:2604.27702v1 Announce Type: new Abstract: Video snapshot compressive imaging (SCI) enables the reconstruction of dynamic scenes from a single snapshot measurement. Recently, NeRF-based methods have shown promising reconstruction performance. However, such methods typically …
arXiv cs.CV TIER_1 English(EN) · Zhenyuan Lin · 2026-04-30 10:48

RayFormer: Modeling Inter- and Intra-Ray Similarity for NeRF-Based Video Snapshot Compressive Imaging

Video snapshot compressive imaging (SCI) enables the reconstruction of dynamic scenes from a single snapshot measurement. Recently, NeRF-based methods have shown promising reconstruction performance. However, such methods typically adopt random ray sampling strategies and fail to…