# The RealDefocus Benchmark for Defocus Deblurring

arXiv: https://arxiv.org/abs/2607.21078 · HTML: https://mlsanity.com/paper/2607.21078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Iterative Filter Adaptive Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2108.13610/) (2021)
- [BokehMe: When Neural Rendering Meets Classical Rendering](https://mlsanity.com/paper/2206.12614/) (2022)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](https://mlsanity.com/paper/2204.00367/) (2022)
- [Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data](https://mlsanity.com/paper/2012.03255/) (2020)
- [Text Recognition in the Wild: A Survey](https://mlsanity.com/paper/2005.03492/) (2020)
- [Efficient Visual State Space Model for Image Deblurring](https://mlsanity.com/paper/2405.14343/) (2024)
- [On Classification of Distorted Images with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.01924/) (2017)
- [Gaussian Kernel Mixture Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2111.00454/) (2021)
- [LiFF: Light Field Features in Scale and Depth](https://mlsanity.com/paper/1901.03916/) (2019)
- [Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures](https://mlsanity.com/paper/2503.16067/) (2025)
- [EAMamba: Efficient All-Around Vision State Space Model for Image Restoration](https://mlsanity.com/paper/2506.22246/) (2025)
- [Revisiting Image Deblurring with an Efficient ConvNet](https://mlsanity.com/paper/2302.02234/) (2023)

## Abstract (arXiv)

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.