# SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction

arXiv: https://arxiv.org/abs/2110.08619 · HTML: https://mlsanity.com/paper/2110.08619/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 16 Oct 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network](https://mlsanity.com/paper/1703.02719/) (2017)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks](https://mlsanity.com/paper/1803.05215/) (2018)
- [Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1809.06323/) (2018)
- [Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor](https://mlsanity.com/paper/2104.09398/) (2021)
- [A Two-stage Deep Network for High Dynamic Range Image Reconstruction](https://mlsanity.com/paper/2104.09386/) (2021)

## Built on by (most cited first, 12 of 12)

- [MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2410.14214/) (2024)
- [Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing](https://mlsanity.com/paper/2503.16134/) (2025)
- [AIM 2022 Challenge on Instagram Filter Removal: Methods and Results](https://mlsanity.com/paper/2210.08997/) (2022)
- [Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors](https://mlsanity.com/paper/2307.10667/) (2023)
- [Inheriting Bayer's Legacy-Joint Remosaicing and Denoising for Quad Bayer Image Sensor](https://mlsanity.com/paper/2303.13571/) (2023)
- [PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors](https://mlsanity.com/paper/2203.04314/) (2022)
- [DarkDeblur: Learning single-shot image deblurring in low-light condition](https://mlsanity.com/paper/2503.02194/) (2025)
- [Two-stage Deep Denoising with Self-guided Noise Attention for Multimodal Medical Images](https://mlsanity.com/paper/2503.06827/) (2025)
- [Lightweight Quad Bayer HybridEVS Demosaicing via State Space Augmented Cross-Attention](https://mlsanity.com/paper/2508.06058/) (2025)
- [An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensors](https://mlsanity.com/paper/2606.13136/) (2026)
- [Deep Perceptual Enhancement for Medical Image Analysis](https://mlsanity.com/paper/2503.08027/) (2025)
- [Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks](https://mlsanity.com/paper/2601.00703/) (2026)

## Abstract (arXiv)

Nona-Bayer colour filter array (CFA) pattern is considered one of the most viable alternatives to traditional Bayer patterns. Despite the substantial advantages, such non-Bayer CFA patterns are susceptible to produce visual artefacts while reconstructing RGB images from noisy sensor data. This study addresses the challenges of learning RGB image reconstruction from noisy Nona-Bayer CFA comprehensively. We propose a novel spatial-asymmetric attention module to jointly learn bi-direction transformation and large-kernel global attention to reduce the visual artefacts. We combine our proposed module with adversarial learning to produce plausible images from Nona-Bayer CFA. The feasibility of the proposed method has been verified and compared with the state-of-the-art image reconstruction method. The experiments reveal that the proposed method can reconstruct RGB images from noisy Nona-Bayer CFA without producing any visually disturbing artefacts. Also, it can outperform the state-of-the-art image reconstruction method in both qualitative and quantitative comparison. Code available: https://github.com/sharif-apu/SAGAN_BMVC21.