# Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather

arXiv: https://arxiv.org/abs/2110.07206 · HTML: https://mlsanity.com/paper/2110.07206/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 30 of 30)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [Image De-raining Using a Conditional Generative Adversarial Network](https://mlsanity.com/paper/1701.05957/) (2017)
- [Towards End-to-End Lane Detection: an Instance Segmentation Approach](https://mlsanity.com/paper/1802.05591/) (2018)
- [Deep Learning on Image Denoising: An overview](https://mlsanity.com/paper/1912.13171/) (2019)
- [Dropout Sampling for Robust Object Detection in Open-Set Conditions](https://mlsanity.com/paper/1710.06677/) (2017)
- [Single Image Deraining: A Comprehensive Benchmark Analysis](https://mlsanity.com/paper/1903.08558/) (2019)
- [Key Points Estimation and Point Instance Segmentation Approach for Lane Detection](https://mlsanity.com/paper/2002.06604/) (2020)
- [HarDNet: A Low Memory Traffic Network](https://mlsanity.com/paper/1909.00948/) (2019)
- [SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation](https://mlsanity.com/paper/1810.01849/) (2018)
- [Physics-Based Rendering for Improving Robustness to Rain](https://mlsanity.com/paper/1908.10335/) (2019)
- [Studying Very Low Resolution Recognition Using Deep Networks](https://mlsanity.com/paper/1601.04153/) (2016)
- [URIE: Universal Image Enhancement for Visual Recognition in the Wild](https://mlsanity.com/paper/2007.08979/) (2020)
- [Benchmarking Image Sensors Under Adverse Weather Conditions for Autonomous Driving](https://mlsanity.com/paper/1912.03238/) (2019)
- [Does Haze Removal Help CNN-based Image Classification?](https://mlsanity.com/paper/1810.05716/) (2018)
- [Rain Removal in Traffic Surveillance: Does it Matter?](https://mlsanity.com/paper/1810.12574/) (2018)
- [Self-Supervised Linear Motion Deblurring](https://mlsanity.com/paper/2002.04070/) (2020)
- [Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform](https://mlsanity.com/paper/2001.11175/) (2020)
- [SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition](https://mlsanity.com/paper/1910.03876/) (2019)
- [Enhance Visual Recognition under Adverse Conditions via Deep Networks](https://mlsanity.com/paper/1712.07732/) (2017)
- [Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles](https://mlsanity.com/paper/2004.01351/) (2020)
- [On the Relation between Color Image Denoising and Classification](https://mlsanity.com/paper/1704.01372/) (2017)

## Built on by (most cited first, 6 of 6)

- [WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions](https://mlsanity.com/paper/2310.05556/) (2023)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [FriendNet: Detection-Friendly Dehazing Network](https://mlsanity.com/paper/2403.04443/) (2024)
- [Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching](https://mlsanity.com/paper/2403.17423/) (2024)
- [Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models](https://mlsanity.com/paper/2508.19850/) (2025)

## Abstract (arXiv)

Visual perception in autonomous driving is a crucial part of a vehicle to navigate safely and sustainably in different traffic conditions. However, in bad weather such as heavy rain and haze, the performance of visual perception is greatly affected by several degrading effects. Recently, deep learning-based perception methods have addressed multiple degrading effects to reflect real-world bad weather cases but have shown limited success due to 1) high computational costs for deployment on mobile devices and 2) poor relevance between image enhancement and visual perception in terms of the model ability. To solve these issues, we propose a task-driven image enhancement network connected to the high-level vision task, which takes in an image corrupted by bad weather as input. Specifically, we introduce a novel low memory network to reduce most of the layer connections of dense blocks for less memory and computational cost while maintaining high performance. We also introduce a new task-driven training strategy to robustly guide the high-level task model suitable for both high-quality restoration of images and highly accurate perception. Experiment results demonstrate that the proposed method improves the performance among lane and 2D object detection, and depth estimation largely under adverse weather in terms of both low memory and accuracy.