Generalized Gaussian Model for Learned Image Compression
This work addresses the need for more efficient probabilistic models in image compression for applications like storage and transmission, but it is incremental as it builds on existing Gaussian-based methods.
The paper tackles the problem of balancing compression performance and complexity in learned image compression by extending the Gaussian model to a generalized Gaussian family with one additional shape parameter, and it demonstrates that this model outperforms Gaussian and Gaussian mixture models on various networks.
In learned image compression, probabilistic models play an essential role in characterizing the distribution of latent variables. The Gaussian model with mean and scale parameters has been widely used for its simplicity and effectiveness. Probabilistic models with more parameters, such as the Gaussian mixture models, can fit the distribution of latent variables more precisely, but the corresponding complexity is higher. To balance the compression performance and complexity, we extend the Gaussian model to the generalized Gaussian family for more flexible latent distribution modeling, introducing only one additional shape parameter beta than the Gaussian model. To enhance the performance of the generalized Gaussian model by alleviating the train-test mismatch, we propose improved training methods, including beta-dependent lower bounds for scale parameters and gradient rectification. Our proposed generalized Gaussian model, coupled with the improved training methods, is demonstrated to outperform the Gaussian and Gaussian mixture models on a variety of learned image compression networks.