构建真实世界失焦去模糊基准，支持模型公平对比
The RealDefocus Benchmark for Defocus Deblurring
- 基于真实数据集构建配对失焦/清晰图像数据集
- 提供训练/验证/测试划分与统一评估框架
- 适合图像恢复与神经渲染方向研究者使用
单图像失焦去模糊（SIDD）旨在从单一失焦观测中恢复全聚焦图像，但因缺乏真实、高分辨率且配准良好的失焦/清晰图像对以及标准化评估协议，导致严格可复现的评估仍具挑战。本文基于真实世界数据集RealBokeh构建RealDefocus基准，提供配对的失焦输入与清晰真值图像，预定义的训练/验证/测试划分，以及统一的评估框架，用于比较图像恢复与神经渲染方法。进一步提出跨数据集验证的基准测试协议，以评估重建质量与泛化能力。项目页面公开于：www.github.com/TimSeizinger/RealDefocus-Benchmark。
原文摘要 · Abstract (English)
Single-Image Defocus Deblurring (SIDD) aims to recover an all-in-focus image from a single defocused observation, but rigorous and reproducible evaluation remains challenging due to the scarcity of realistic, high-resolution datasets with well-aligned defocused/sharp pairs and standardized protocols. We build on RealDefocus, a benchmark derived from the real-world RealBokeh dataset originally proposed for Bokeh Rendering. RealDefocus provides paired defocused inputs and sharp ground truth images, predefined training/validation/test splits, and a unified evaluation framework for comparing image restoration and neural rendering approaches. We further outline a benchmarking protocol with cross-dataset validation to assess reconstruction quality and generalization. The project page is publicly available at: www.github.com/TimSeizinger/RealDefocus-Benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。