Researchers have introduced RayFormer, a novel approach for video snapshot compressive imaging (SCI) that improves reconstruction quality. This method utilizes a patch-level ray sampling strategy and an Inter- and Intra-Ray Transformer to better capture structural similarities within dynamic scenes. By modeling both spatial and depth-wise correlations, RayFormer achieves state-of-the-art performance in reconstructing scenes from single snapshot measurements. AI
影响 Introduces a novel transformer-based method for improved video reconstruction from single snapshots.
排序理由 This is a research paper detailing a new method for video snapshot compressive imaging.
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
