# Deep Smoke Segmentation

arXiv: https://arxiv.org/abs/1809.00774 · HTML: https://mlsanity.com/paper/1809.00774/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2018.

## Built on by (most cited first, 12 of 12)

- [Exploring Color Invariance through Image-Level Ensemble Learning](https://mlsanity.com/paper/2401.10512/) (2024)
- [FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection](https://mlsanity.com/paper/2112.08598/) (2021)
- [Transmission-Guided Bayesian Generative Model for Smoke Segmentation](https://mlsanity.com/paper/2303.00900/) (2023)
- [FoSp: Focus and Separation Network for Early Smoke Segmentation](https://mlsanity.com/paper/2306.04474/) (2023)
- [Deep Convolutional Neural Network for Plume Rise Measurements in Industrial Environments](https://mlsanity.com/paper/2302.07416/) (2023)
- [Wildfire smoke plume segmentation using geostationary satellite imagery](https://mlsanity.com/paper/2109.01637/) (2021)
- [SmokeNet: Efficient Smoke Segmentation Leveraging Multiscale Convolutions and Multiview Attention Mechanisms](https://mlsanity.com/paper/2502.12258/) (2025)
- [MGFI-Net: A Multi-Grained Feature Integration Network for Enhanced Medical Image Segmentation](https://mlsanity.com/paper/2502.13808/) (2025)
- [Generative AI for Enhanced Wildfire Detection: Bridging the Synthetic-Real Domain Gap](https://mlsanity.com/paper/2511.16617/) (2025)
- [Contour Refinement using Discrete Diffusion in Low Data Regime](https://mlsanity.com/paper/2602.05880/) (2026)
- [Hyperspectral Smoke Segmentation via Mixture of Prototypes](https://mlsanity.com/paper/2602.10858/) (2026)
- [AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset](https://mlsanity.com/paper/2604.23542/) (2026)

## Abstract (arXiv)

Inspired by the recent success of fully convolutional networks (FCN) in semantic segmentation, we propose a deep smoke segmentation network to infer high quality segmentation masks from blurry smoke images. To overcome large variations in texture, color and shape of smoke appearance, we divide the proposed network into a coarse path and a fine path. The first path is an encoder-decoder FCN with skip structures, which extracts global context information of smoke and accordingly generates a coarse segmentation mask. To retain fine spatial details of smoke, the second path is also designed as an encoder-decoder FCN with skip structures, but it is shallower than the first path network. Finally, we propose a very small network containing only add, convolution and activation layers to fuse the results of the two paths. Thus, we can easily train the proposed network end to end for simultaneous optimization of network parameters. To avoid the difficulty in manually labelling fuzzy smoke objects, we propose a method to generate synthetic smoke images. According to results of our deep segmentation method, we can easily and accurately perform smoke detection from videos. Experiments on three synthetic smoke datasets and a realistic smoke dataset show that our method achieves much better performance than state-of-the-art segmentation algorithms based on FCNs. Test results of our method on videos are also appealing.