# Learning Digital Camera Pipeline for Extreme Low-Light Imaging

arXiv: https://arxiv.org/abs/1904.05939 · HTML: https://mlsanity.com/paper/1904.05939/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Burst Image Restoration and Enhancement](https://mlsanity.com/paper/2110.03680/) (2021)
- [Burstormer: Burst Image Restoration and Enhancement Transformer](https://mlsanity.com/paper/2304.01194/) (2023)
- [Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment](https://mlsanity.com/paper/2406.14360/) (2024)
- [Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement](https://mlsanity.com/paper/2304.06703/) (2023)
- [Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement](https://mlsanity.com/paper/2409.07040/) (2024)
- [Frequency Domain Loss Function for Deep Exposure Correction of Dark Images](https://mlsanity.com/paper/2104.10856/) (2021)
- [DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images](https://mlsanity.com/paper/2402.18575/) (2023)
- [Low Light Image Enhancement via Global and Local Context Modeling](https://mlsanity.com/paper/2101.00850/) (2021)
- [LW-ISP: A Lightweight Model with ISP and Deep Learning](https://mlsanity.com/paper/2210.03904/) (2022)

## Abstract (arXiv)

In low-light conditions, a conventional camera imaging pipeline produces sub-optimal images that are usually dark and noisy due to a low photon count and low signal-to-noise ratio (SNR). We present a data-driven approach that learns the desired properties of well-exposed images and reflects them in images that are captured in extremely low ambient light environments, thereby significantly improving the visual quality of these low-light images. We propose a new loss function that exploits the characteristics of both pixel-wise and perceptual metrics, enabling our deep neural network to learn the camera processing pipeline to transform the short-exposure, low-light RAW sensor data to well-exposed sRGB images. The results show that our method outperforms the state-of-the-art according to psychophysical tests as well as pixel-wise standard metrics and recent learning-based perceptual image quality measures.