# Deep Atrous Guided Filter for Image Restoration in Under Display Cameras

arXiv: https://arxiv.org/abs/2008.06229 · HTML: https://mlsanity.com/paper/2008.06229/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring](https://mlsanity.com/paper/2404.13153/) (2024)
- [Under-Display Camera Image Restoration with Scattering Effect](https://mlsanity.com/paper/2308.04163/) (2023)
- [Modular Degradation Simulation and Restoration for Under-Display Camera](https://mlsanity.com/paper/2209.11455/) (2022)
- [Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer](https://mlsanity.com/paper/2308.10196/) (2023)
- [ISP-Agnostic Image Reconstruction for Under-Display Cameras](https://mlsanity.com/paper/2111.01511/) (2021)
- [Deep Video Restoration for Under-Display Camera](https://mlsanity.com/paper/2309.04752/) (2023)
- [Zero-Reference Image Restoration for Under-Display Camera of UAV](https://mlsanity.com/paper/2202.06283/) (2022)
- [Adversarial Purification and Fine-tuning for Robust UDC Image Restoration](https://mlsanity.com/paper/2402.13629/) (2024)
- [Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration](https://mlsanity.com/paper/2403.05906/) (2024)
- [UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration](https://mlsanity.com/paper/2604.00381/) (2026)

## Abstract (arXiv)

Under Display Cameras present a promising opportunity for phone manufacturers to achieve bezel-free displays by positioning the camera behind semi-transparent OLED screens. Unfortunately, such imaging systems suffer from severe image degradation due to light attenuation and diffraction effects. In this work, we present Deep Atrous Guided Filter (DAGF), a two-stage, end-to-end approach for image restoration in UDC systems. A Low-Resolution Network first restores image quality at low-resolution, which is subsequently used by the Guided Filter Network as a filtering input to produce a high-resolution output. Besides the initial downsampling, our low-resolution network uses multiple, parallel atrous convolutions to preserve spatial resolution and emulates multi-scale processing. Our approach's ability to directly train on megapixel images results in significant performance improvement. We additionally propose a simple simulation scheme to pre-train our model and boost performance. Our overall framework ranks 2nd and 5th in the RLQ-TOD'20 UDC Challenge for POLED and TOLED displays, respectively.