# Multi-Task Learning for Screen Content Image Coding

arXiv: https://arxiv.org/abs/2302.02014 · HTML: https://mlsanity.com/paper/2302.02014/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2023.

## Built on by (most cited first, 4 of 4)

- [PICD: Versatile Perceptual Image Compression with Diffusion Rendering](https://mlsanity.com/paper/2505.05853/) (2025)
- [Learned Image Compression with Text Quality Enhancement](https://mlsanity.com/paper/2402.08643/) (2024)
- [OMR-NET: a two-stage octave multi-scale residual network for screen content image compression](https://mlsanity.com/paper/2407.08545/) (2024)
- [FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression](https://mlsanity.com/paper/2502.15174/) (2025)

## Abstract (arXiv)

With the rise of remote work and collaboration, compression of screen content images (SCI) is becoming increasingly important. While there are efficient codecs for natural images, as well as codecs for purely-synthetic images, those SCIs that contain both synthetic and natural content pose a particular challenge. In this paper, we propose a learning-based image coding model developed for such SCIs. By training an encoder to provide a latent representation suitable for two tasks -- input reconstruction and synthetic/natural region segmentation -- we create an effective SCI image codec whose strong performance is verified through experiments. Once trained, the second task (segmentation) need not be used; the codec still benefits from the segmentation-friendly latent representation.