๐Ÿ“–
Semantic-Guided Frequency Modulation for Learned Image Compression
Gangyi Tian, Wen Ji, Alireza Furutanpey, Mingxuan Li

Semantic-Guided Frequency Modulation for Learned Image Compression

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

High-frequency attenuation can reduce the rate of learned image codecs but also remove object boundaries and fine detail. We propose Semantic-Guided Adaptive Latent-Frequency Modulation (SG-AFM), which uses a semantic structural prior to guide attenuation of encoder latents. SG-AFM applies a Haar wavelet transform and combines a fixed semantic-frequency multiplier with a bounded learned correction to modulate high-frequency subbands. The semantic prior is computed only at the encoder. No semantic map is transmitted, and no decoder modules are added. Across six datasets, SG-AFM reduces PSNR-based BD-rate relative to TCM by an average of 13.17%. It achieves the best BD-rate among the compared methods on ExDark, NightCity, and OnePlus, with a mean reduction of 16.80%. An ablation on OnePlus demonstrates the benefit of spatially aligned semantic guidance, and visual comparisons illustrate improved reconstruction of local structures.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title Semantic-Guided Frequency Modulation for Learned Image Compression
Author / Organization Gangyi Tian, Wen Ji, Alireza Furutanpey, Mingxuan Li
Subject & Discipline eess.IV
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-114543
Original Source Link Visit Source Page on arxiv.org »