# GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions

arXiv: https://arxiv.org/abs/2209.14922 · HTML: https://mlsanity.com/paper/2209.14922/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 29 Sep 2022.

## Builds on (most cited first, 25 of 25)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation](https://mlsanity.com/paper/2005.14553/) (2020)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement](https://mlsanity.com/paper/2110.00970/) (2021)
- [Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN](https://mlsanity.com/paper/2007.01571/) (2020)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection](https://mlsanity.com/paper/2003.04132/) (2020)
- [PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation](https://mlsanity.com/paper/2108.07142/) (2021)
- [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017)
- [Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.01483/) (2021)
- [Domain Adaptive YOLO for One-Stage Cross-Domain Detection](https://mlsanity.com/paper/2106.13939/) (2021)

## Built on by (most cited first, 20 of 20)

- [PE-YOLO: Pyramid Enhancement Network for Dark Object Detection](https://mlsanity.com/paper/2307.10953/) (2023)
- [You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection](https://mlsanity.com/paper/2410.18398/) (2024)
- [ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing](https://mlsanity.com/paper/2411.02799/) (2024)
- [DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions](https://mlsanity.com/paper/2306.17536/) (2023)
- [DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision](https://mlsanity.com/paper/2309.06941/) (2023)
- [CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations](https://mlsanity.com/paper/2403.11220/) (2024)
- [WARLearn: Weather-Adaptive Representation Learning](https://mlsanity.com/paper/2411.14095/) (2024)
- [Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL](https://mlsanity.com/paper/2511.12755/) (2025)
- [DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions](https://mlsanity.com/paper/2309.08152/) (2023)
- [DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions](https://mlsanity.com/paper/2310.04181/) (2023)
- [UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers](https://mlsanity.com/paper/2506.12324/) (2025)
- [FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network](https://mlsanity.com/paper/2510.23444/) (2025)
- [Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy](https://mlsanity.com/paper/2510.24232/) (2025)
- [Language Prompt vs. Image Enhancement: Boosting Object Detection With CLIP in Hazy Environments](https://mlsanity.com/paper/2604.10637/) (2026)
- [AMIEOD: Adaptive Multi-Experts Image Enhancement for Object Detection in Low-Illumination Scenes](https://mlsanity.com/paper/2605.06084/) (2026)
- [Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection](https://mlsanity.com/paper/2606.26828/) (2026)
- [FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather](https://mlsanity.com/paper/2606.30471/) (2026)
- [YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling](https://mlsanity.com/paper/2608.15713/) (2026)
- [TaskGuard: Task-Conditioned Restoration Utility for Risk-Aware Object Detection](https://mlsanity.com/paper/2609.08011/) (2026)
- [C2FXNet: Coarse-to-Fine Scene Expert for Unified Object Detection across Adverse Weather](https://mlsanity.com/paper/2609.25693/) (2026)

## Abstract (arXiv)

Detecting objects under adverse weather and lighting conditions is crucial for the safe and continuous operation of an autonomous vehicle, and remains an unsolved problem. We present a Gated Differentiable Image Processing (GDIP) block, a domain-agnostic network architecture, which can be plugged into existing object detection networks (e.g., Yolo) and trained end-to-end with adverse condition images such as those captured under fog and low lighting. Our proposed GDIP block learns to enhance images directly through the downstream object detection loss. This is achieved by learning parameters of multiple image pre-processing (IP) techniques that operate concurrently, with their outputs combined using weights learned through a novel gating mechanism. We further improve GDIP through a multi-stage guidance procedure for progressive image enhancement. Finally, trading off accuracy for speed, we propose a variant of GDIP that can be used as a regularizer for training Yolo, which eliminates the need for GDIP-based image enhancement during inference, resulting in higher throughput and plausible real-world deployment. We demonstrate significant improvement in detection performance over several state-of-the-art methods through quantitative and qualitative studies on synthetic datasets such as PascalVOC, and real-world foggy (RTTS) and low-lighting (ExDark) datasets.