# Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

arXiv: https://arxiv.org/abs/2103.06501 · HTML: https://mlsanity.com/paper/2103.06501/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 11 Mar 2021.

## Builds on (most cited first, 23 of 23)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Image De-raining Using a Conditional Generative Adversarial Network](https://mlsanity.com/paper/1701.05957/) (2017)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Disentangling factors of variation in deep representations using adversarial training](https://mlsanity.com/paper/1611.03383/) (2016)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018)
- [Generative Image Modeling using Style and Structure Adversarial Networks](https://mlsanity.com/paper/1603.05631/) (2016)
- [Multi-mapping Image-to-Image Translation via Learning Disentanglement](https://mlsanity.com/paper/1909.07877/) (2019)
- [Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs](https://mlsanity.com/paper/1807.01001/) (2018)
- [To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene](https://mlsanity.com/paper/1912.06556/) (2019)

## Built on by (most cited first, 2 of 2)

- [BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation](https://mlsanity.com/paper/2504.05137/) (2025)
- [Low-cost Robust Night-time Aerial Material Segmentation through Hyperspectral Data and Sparse Spatio-Temporal Learning](https://mlsanity.com/paper/2410.15208/) (2024)

## Abstract (arXiv)

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i.e.style feature, and the feature representing the invariant semantic content, i.e. content feature. Previous methods separate content feature apart by utilizing it to classify haze image during the training process. However, in this paper we recognize the incompleteness of the content-style disentanglement in such technical routine. The flawed style feature entangled with content information inevitably leads the ill-rendering of the haze images. To address, we propose a self-supervised style regression via stochastic linear interpolation to reduce the content information in style feature. The ablative experiments demonstrate the disentangling completeness and its superiority in level-aware haze image synthesis. Moreover, the generated haze data are applied in the testing generalization of vehicle detectors. Further study between haze-level and detection performance shows that haze has obvious impact on the generalization of the vehicle detectors and such performance degrading level is linearly correlated to the haze-level, which, in turn, validates the effectiveness of the proposed method.