# SELIC: Semantic-Enhanced Learned Image Compression via High-Level Textual Guidance

arXiv: https://arxiv.org/abs/2504.01279 · HTML: https://mlsanity.com/paper/2504.01279/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2025.

## Built on by (most cited first, 1 of 1)

- [Low-Bitrate Video Compression through Semantic-Conditioned Diffusion](https://mlsanity.com/paper/2512.00408/) (2025)

## Abstract (arXiv)

Learned image compression (LIC) techniques have achieved remarkable progress; however, effectively integrating high-level semantic information remains challenging. In this work, we present a underlineSemantic-underlineEnhanced underlineLearned underlineImage underlineCompression framework, termed SELIC, which leverages high-level textual guidance to improve rate-distortion performance. Specifically, SELIC employs a text encoder to extract rich semantic descriptions from the input image. These textual features are transformed into fixed-dimension tensors and seamlessly fused with the image-derived latent representation. By embedding the SELIC tensor directly into the compression pipeline, our approach enriches the bitstream without requiring additional inputs at the decoder, thereby maintaining fast and efficient decoding. Extensive experiments on benchmark datasets (e.g., Kodak) demonstrate that integrating semantic information substantially enhances compression quality. Our SELIC-guided method outperforms a baseline LIC model without semantic integration by approximately 0.1-0.15 dB across a wide range of bit rates in PSNR and achieves a 4.9% BD-rate improvement over VVC. Moreover, this improvement comes with minimal computational overhead, making the proposed SELIC framework a practical solution for advanced image compression applications.