# Learning Dual-Pixel Alignment for Defocus Deblurring

arXiv: https://arxiv.org/abs/2204.12105 · HTML: https://mlsanity.com/paper/2204.12105/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 26 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Learning Single Camera Depth Estimation using Dual-Pixels](https://mlsanity.com/paper/1904.05822/) (2019)
- [Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data](https://mlsanity.com/paper/2012.03255/) (2020)
- [DAVANet: Stereo Deblurring with View Aggregation](https://mlsanity.com/paper/1904.05065/) (2019)
- [Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration](https://mlsanity.com/paper/2012.00301/) (2020)
- [Learning to Autofocus](https://mlsanity.com/paper/2004.12260/) (2020)
- [A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation](https://mlsanity.com/paper/1704.08992/) (2017)
- [Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels](https://mlsanity.com/paper/2003.14299/) (2020)

## Built on by (most cited first, 5 of 5)

- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)
- [Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark](https://mlsanity.com/paper/2211.00859/) (2022)
- [Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation](https://mlsanity.com/paper/2503.11213/) (2025)
- [SDI-Net: Toward Sufficient Dual-View Interaction for Low-light Stereo Image Enhancement](https://mlsanity.com/paper/2408.10934/) (2024)
- [FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation](https://mlsanity.com/paper/2607.01900/) (2026)

## Abstract (arXiv)

It is a challenging task to recover sharp image from a single defocus blurry image in real-world applications. On many modern cameras, dual-pixel (DP) sensors create two-image views, based on which stereo information can be exploited to benefit defocus deblurring. Despite the impressive results achieved by existing DP defocus deblurring methods, the misalignment between DP image views is still not studied, leaving room for improving DP defocus deblurring. In this work, we propose a Dual-Pixel Alignment Network (DPANet) for defocus deblurring. Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the sharp image. Due to that DP views suffer from different blur amounts, it is not trivial to align left and right views. To this end, we propose novel encoder alignment module (EAM) and decoder alignment module (DAM). In particular, a correlation layer is suggested in EAM to measure the disparity between DP views, whose deep features can then be accordingly aligned using deformable convolutions. DAM can further enhance the alignment of skip-connected features from encoder and deep features in decoder. By introducing several EAMs and DAMs, DP views in DPANet can be well aligned for better predicting latent sharp image. Experimental results on real-world datasets show that our DPANet is notably superior to state-of-the-art deblurring methods in reducing defocus blur while recovering visually plausible sharp structures and textures.