Approximately Invertible Neural Network for Learned Image Compression
IEEE Transactions on Image Processing · 2025 · 34 · 3041-3055
DOI: 10.1109/tip.2025.3567830 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Yanbo Gao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Learned image compression has attracted considerable interests in recent years. An analysis transform and a synthesis transform, which can be regarded as coupled transforms, are used to encode an image to latent feature and decode the feature after quantization to reconstruct the image. Inspired by the success of invertible neural networks in generative modeling, invertible modules can be used to construct the coupled analysis and synthesis transforms. Considering the noise introduced in the feature quantization invalidates the invertible process, this paper proposes an Approximately Invertible Neural Network (A-INN) framework for learned image compression. It formulates the rate-distortion optimization in lossy image compression when using INN with quantization, which differentiates from using INN for generative modelling. Generally speaking, A-INN can be used as the theoretical foundation for any INN based lossy compression method. Based on this formulation, A-INN with a progressive denoising module (PDM) is developed to effectively reduce the quantization noise in the decoding. Moreover, a Cascaded Feature Recovery Module (CFRM) is designed to learn high-dimensional feature recovery from low-dimensional ones to further reduce the noise in feature channel compression. In addition, a Frequency-enhanced Decomposition and Synthesis Module (FDSM) is developed by explicitly enhancing the high-frequency components in an image to address the loss of high-frequency information inherent in neural network based image compression, thereby enhancing the reconstructed image quality. Extensive experiments demonstrate that the proposed A-INN framework achieves better or comparable compression efficiency than the conventional image compression approach and state-of-the-art learned image compression methods.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
Zitieren
APA
Gao, Y., Li, S., Fu, M., Lv, C., Yang, Z., Cai, X., Yuan, H., & Ye, M. (2025). Approximately Invertible Neural Network for Learned Image Compression. IEEE Transactions on Image Processing, 34, 3041-3055. https://doi.org/10.1109/tip.2025.3567830
Vancouver
Gao Y, Li S, Fu M, Lv C, Yang Z, Cai X, et al. Approximately Invertible Neural Network for Learned Image Compression. IEEE Transactions on Image Processing. 2025;34:3041-3055. doi:10.1109/tip.2025.3567830
BibTeX
@article{Gao2025,
author = {Gao, Yanbo and Li, Shuai and Fu, Meng and Lv, Chong and Yang, Zhiyuan and Cai, Xun and Yuan, Hui and Ye, Mao},
title = {Approximately Invertible Neural Network for Learned Image Compression},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {3041--3055},
doi = {10.1109/tip.2025.3567830}
}
EUVIMED