# Day-to-Night Image Synthesis for Training Nighttime Neural ISPs

arXiv: https://arxiv.org/abs/2206.02715 · HTML: https://mlsanity.com/paper/2206.02715/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 6 Jun 2022.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [DualGAN: Unsupervised Dual Learning for Image-to-Image Translation](https://mlsanity.com/paper/1704.02510/) (2017)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021)
- [Night-to-Day Image Translation for Retrieval-based Localization](https://mlsanity.com/paper/1809.09767/) (2018)
- [Deep Burst Denoising](https://mlsanity.com/paper/1712.05790/) (2017)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night](https://mlsanity.com/paper/1907.08719/) (2019)
- [See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion](https://mlsanity.com/paper/1908.05868/) (2019)
- [Sensor-Independent Illumination Estimation for DNN Models](https://mlsanity.com/paper/1912.06888/) (2019)

## Built on by (most cited first, 23 of 23)

- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [ExposureDiffusion: Learning to Expose for Low-light Image Enhancement](https://mlsanity.com/paper/2307.07710/) (2023)
- [DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition](https://mlsanity.com/paper/2211.01146/) (2022)
- [Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments](https://mlsanity.com/paper/2210.16046/) (2022)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs](https://mlsanity.com/paper/2404.10700/) (2024)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [AGI for Agriculture](https://mlsanity.com/paper/2304.06136/) (2023)
- [SVNR: Spatially-variant Noise Removal with Denoising Diffusion](https://mlsanity.com/paper/2306.16052/) (2023)
- [Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions](https://mlsanity.com/paper/2407.15451/) (2024)
- [RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling](https://mlsanity.com/paper/2605.05941/) (2026)
- [PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality](https://mlsanity.com/paper/2403.10091/) (2024)
- [TS-Diff: Two-Stage Diffusion Model for Low-Light RAW Image Enhancement](https://mlsanity.com/paper/2505.04281/) (2025)
- [RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes](https://mlsanity.com/paper/2601.05249/) (2026)
- [ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving Scenes](https://mlsanity.com/paper/2408.12048/) (2024)
- [Sun Off, Lights On: Photorealistic Monocular Nighttime Simulation for Robust Semantic Perception](https://mlsanity.com/paper/2407.20336/) (2024)
- [NPSim: Nighttime Photorealistic Simulation From Daytime Images With Monocular Inverse Rendering and Ray Tracing](https://mlsanity.com/paper/2502.10720/) (2025)
- [Diffusion-Guided Knowledge Distillation for Weakly-Supervised Low-Light Semantic Segmentation](https://mlsanity.com/paper/2507.07578/) (2025)
- [Benchmarking Nighttime Traffic Sign Recognition with Illumination-Adaptive Detection and Semantic Attribute Reasoning](https://mlsanity.com/paper/2511.17183/) (2025)
- [RawGen: Learning Camera Raw Image Generation](https://mlsanity.com/paper/2604.00093/) (2026)
- [Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement](https://mlsanity.com/paper/2608.23136/) (2026)
- [Benchmarking RAW and RGB Restoration in Image Signal Processors](https://mlsanity.com/paper/2609.02831/) (2026)
- [RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation](https://mlsanity.com/paper/2609.37530/) (2026)

## Abstract (arXiv)

Many flagship smartphone cameras now use a dedicated neural image signal processor (ISP) to render noisy raw sensor images to the final processed output. Training nightmode ISP networks relies on large-scale datasets of image pairs with: (1) a noisy raw image captured with a short exposure and a high ISO gain; and (2) a ground truth low-noise raw image captured with a long exposure and low ISO that has been rendered through the ISP. Capturing such image pairs is tedious and time-consuming, requiring careful setup to ensure alignment between the image pairs. In addition, ground truth images are often prone to motion blur due to the long exposure. To address this problem, we propose a method that synthesizes nighttime images from daytime images. Daytime images are easy to capture, exhibit low-noise (even on smartphone cameras) and rarely suffer from motion blur. We outline a processing framework to convert daytime raw images to have the appearance of realistic nighttime raw images with different levels of noise. Our procedure allows us to easily produce aligned noisy and clean nighttime image pairs. We show the effectiveness of our synthesis framework by training neural ISPs for nightmode rendering. Furthermore, we demonstrate that using our synthetic nighttime images together with small amounts of real data (e.g., 5% to 10%) yields performance almost on par with training exclusively on real nighttime images. Our dataset and code are available at https://github.com/SamsungLabs/day-to-night.