研究人员开发了 GTF，一种用于光场图像超分辨率的全向 EPI Transformer。该新模型明确地融入了对角线外极几何，这在以前的类似方法中未被充分探索。GTF 在标准基准测试中取得了强劲的性能，达到 32.78 dB，并且一个轻量级变体 GTF-Tiny 也通过低参数量展示了效率。GTF 模型及其变体在 NTIRE 2026 光场图像超分辨率挑战赛中获得了有竞争力的排名。 AI
影响 通过融入对角线外极几何，为光场超分辨率引入了一种新颖的方法，有可能提高使用光场数据的应用中的图像质量。
排序理由 该集群包含一篇 arXiv 论文，详细介绍了新模型及其在基准测试和挑战赛中的表现。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.04581v1 Announce Type: new Abstract: Light field (LF) image super-resolution benefits from Epipolar Plane Images (EPIs), whose line slopes explicitly encode disparity. However, existing Transformer-based LF SR methods mainly attend to horizontal and vertical EPIs, leav…
Light field (LF) image super-resolution benefits from Epipolar Plane Images (EPIs), whose line slopes explicitly encode disparity. However, existing Transformer-based LF SR methods mainly attend to horizontal and vertical EPIs, leaving diagonal epipolar geometry underexplored. We…