# Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data

arXiv: https://arxiv.org/abs/2012.03255 · HTML: https://mlsanity.com/paper/2012.03255/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2020.

## Built on by (most cited first, 30 of 42)

- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Improving Image Restoration by Revisiting Global Information Aggregation](https://mlsanity.com/paper/2112.04491/) (2021)
- [WaveDM: Wavelet-Based Diffusion Models for Image Restoration](https://mlsanity.com/paper/2305.13819/) (2023)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](https://mlsanity.com/paper/2204.00367/) (2022)
- [Improving Image Restoration through Removing Degradations in Textual Representations](https://mlsanity.com/paper/2312.17334/) (2023)
- [SPIRE: Semantic Prompt-Driven Image Restoration](https://mlsanity.com/paper/2312.11595/) (2023)
- [DC2: Dual-Camera Defocus Control by Learning to Refocus](https://mlsanity.com/paper/2304.03285/) (2023)
- [Facial Depth and Normal Estimation using Single Dual-Pixel Camera](https://mlsanity.com/paper/2111.12928/) (2021)
- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)
- [Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures](https://mlsanity.com/paper/2503.16067/) (2025)
- [Image Deblurring by Exploring In-depth Properties of Transformer](https://mlsanity.com/paper/2303.15198/) (2023)
- [Revisiting Image Deblurring with an Efficient ConvNet](https://mlsanity.com/paper/2302.02234/) (2023)
- [Masked Autoencoders as Image Processors](https://mlsanity.com/paper/2303.17316/) (2023)
- [Learning Single Image Defocus Deblurring with Misaligned Training Pairs](https://mlsanity.com/paper/2211.14502/) (2022)
- [IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions](https://mlsanity.com/paper/2404.00633/) (2024)
- [Dual-Pixel Raindrop Removal](https://mlsanity.com/paper/2210.13321/) (2022)
- [Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging](https://mlsanity.com/paper/2402.18102/) (2024)
- [Dynamic Neural Radiance Field From Defocused Monocular Video](https://mlsanity.com/paper/2407.05586/) (2024)
- [Learning Dual-Pixel Alignment for Defocus Deblurring](https://mlsanity.com/paper/2204.12105/) (2022)
- [Enhancing Image Restoration Transformer via Adaptive Translation Equivariance](https://mlsanity.com/paper/2506.18520/) (2025)
- [Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network](https://mlsanity.com/paper/2111.12971/) (2021)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels](https://mlsanity.com/paper/2111.07837/) (2021)
- [Continuous Cost Aggregation for Dual-Pixel Disparity Extraction](https://mlsanity.com/paper/2306.07921/) (2023)
- [Efficient Image Deblurring Networks based on Diffusion Models](https://mlsanity.com/paper/2401.05907/) (2024)
- [Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention](https://mlsanity.com/paper/2505.16157/) (2025)
- [DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer](https://mlsanity.com/paper/2209.06040/) (2022)
- [F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring](https://mlsanity.com/paper/2409.02056/) (2024)

## Abstract (arXiv)

Recent work has shown impressive results on data-driven defocus deblurring using the two-image views available on modern dual-pixel (DP) sensors. One significant challenge in this line of research is access to DP data. Despite many cameras having DP sensors, only a limited number provide access to the low-level DP sensor images. In addition, capturing training data for defocus deblurring involves a time-consuming and tedious setup requiring the camera's aperture to be adjusted. Some cameras with DP sensors (e.g., smartphones) do not have adjustable apertures, further limiting the ability to produce the necessary training data. We address the data capture bottleneck by proposing a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a recurrent convolutional network (RCN) architecture that improves deblurring results and is suitable for use with single-frame and multi-frame data (e.g., video) captured by DP sensors. Finally, we show that our synthetic DP data is useful for training DNN models targeting video deblurring applications where access to DP data remains challenging.