# GenISP: Neural ISP for Low-Light Machine Cognition

arXiv: https://arxiv.org/abs/2205.03688 · HTML: https://mlsanity.com/paper/2205.03688/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 7 May 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [CameraNet: A Two-Stage Framework for Effective Camera ISP Learning](https://mlsanity.com/paper/1908.01481/) (2019)
- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [Recurrent Exposure Generation for Low-Light Face Detection](https://mlsanity.com/paper/2007.10963/) (2020)
- [Towards Fast and Light-Weight Restoration of Dark Images](https://mlsanity.com/paper/2011.14133/) (2020)
- [NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset](https://mlsanity.com/paper/2110.10364/) (2021)

## Built on by (most cited first, 22 of 22)

- [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)
- [Raw or Cooked? Object Detection on RAW Images](https://mlsanity.com/paper/2301.08965/) (2023)
- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2405.11478/) (2024)
- [Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection](https://mlsanity.com/paper/2303.13916/) (2023)
- [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025)
- [DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images](https://mlsanity.com/paper/2402.18575/) (2023)
- [Beyond RGB: Adaptive Parallel Processing for RAW Object Detection](https://mlsanity.com/paper/2503.13163/) (2025)
- [A Learnable Color Correction Matrix for RAW Reconstruction](https://mlsanity.com/paper/2409.02497/) (2024)
- [Examining Autoexposure for Challenging Scenes](https://mlsanity.com/paper/2309.04542/) (2023)
- [Leveraging Content and Context Cues for Low-Light Image Enhancement](https://mlsanity.com/paper/2412.07693/) (2024)
- [SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements](https://mlsanity.com/paper/2503.07101/) (2025)
- [γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition](https://mlsanity.com/paper/2509.22448/) (2025)
- [RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images](https://mlsanity.com/paper/2602.03760/) (2026)
- [UniISP: A Unified ISP Framework for Both Human and Machine Vision](https://mlsanity.com/paper/2605.07359/) (2026)
- [Raw Instinct: Trust Your Classifiers and Skip the Conversion](https://mlsanity.com/paper/2403.14439/) (2024)
- [UNICE: Training A Universal Image Contrast Enhancer](https://mlsanity.com/paper/2507.17157/) (2025)
- [Spatial-Frequency Aware for Object Detection in RAW Image](https://mlsanity.com/paper/2508.01396/) (2025)
- [SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras](https://mlsanity.com/paper/2603.14885/) (2026)
- [FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection](https://mlsanity.com/paper/2608.03385/) (2026)
- [RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation](https://mlsanity.com/paper/2609.37530/) (2026)

## Abstract (arXiv)

Object detection in low-light conditions remains a challenging but important problem with many practical implications. Some recent works show that, in low-light conditions, object detectors using raw image data are more robust than detectors using image data processed by a traditional ISP pipeline. To improve detection performance in low-light conditions, one can fine-tune the detector to use raw image data or use a dedicated low-light neural pipeline trained with paired low- and normal-light data to restore and enhance the image. However, different camera sensors have different spectral sensitivity and learning-based models using raw images process data in the sensor-specific color space. Thus, once trained, they do not guarantee generalization to other camera sensors. We propose to improve generalization to unseen camera sensors by implementing a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space. We also propose a two-stage color processing implemented by two image-to-parameter modules that take down-sized image as input and regress global color correction parameters. Moreover, we propose to train our proposed GenISP under the guidance of a pre-trained object detector and avoid making assumptions about perceptual quality of the image, but rather optimize the image representation for machine cognition. At the inference stage, GenISP can be paired with any object detector. We perform extensive experiments to compare our method to other low-light image restoration and enhancement methods in an extrinsic task-based evaluation and validate that GenISP can generalize to unseen sensors and object detectors. Finally, we contribute a low-light dataset of 7K raw images annotated with 46K bounding boxes for task-based benchmarking of future low-light image restoration and object detection.