Semantic Prior-Guided Scalable Image Coding

We propose a semantic priori-guided scalable image coding method for simultaneously supporting fast machine vision analysis and high quality human visual experience. To obtain high-performance machine vision analysis results with a more compact base layer bitrate, our base layer directly encodes int...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 1 - 5
Hauptverfasser: Shi, Wuzhen, Yin, Wennan, Tao, Fei, Wen, Yang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.04.2025
Schlagworte:
Bit rate
Deep learning
Feature Domain Residual Encoding
Image coding
Image reconstruction
Machine vision
Noise
Object detection
Scalable Image Coding
Semantic Prior
Semantics
Speech processing
Structural Reparameterization
Visualization
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a semantic priori-guided scalable image coding method for simultaneously supporting fast machine vision analysis and high quality human visual experience. To obtain high-performance machine vision analysis results with a more compact base layer bitrate, our base layer directly encodes intermediate semantic features of the pre-trained machine vision task network, which effectively reduces the impact of the information needed for the human vision task. To improve model performance while quickly supporting machine vision tasks, we use structural re-parameterization technology to optimize the model. Considering that the base layer's semantic features can effectively reflect the regions of important image content, we use the semantic prior provided by the base layer to guide the enhancement layer encoding and decoding, which allows us to pay more attention to the reconstruction of semantically important regions. In addition, we use the base layer features to predict the enhancement layer features for performing feature-domain residual coding, which further reduces the bitrate and also reduces the effect of noise compared to pixel-domain residual coding. Extensive experimental results show that our method achieves significant advantages in both object detection performance and image reconstruction tasks compared with BPG and state-of-the-art deep learning-based scalable image coding methods.
ISSN:2379-190X
DOI:10.1109/ICASSP49660.2025.10890628