Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression
This addresses the problem of efficient and flexible image compression for applications requiring high-quality encoding, representing a significant advancement rather than an incremental improvement.
The paper tackles the limitations of autoencoder-based learned image compression at high bit rates and rate adaptation by proposing a variable-rate model using a multi-scale invertible neural network, achieving state-of-the-art performance and outperforming VVC across a wide range of bit rates with a single model.
Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distortion performance at high bit rates and restricts their flexibility of rate adaptation. In this paper, we present a variable-rate image compression model based on invertible transform to overcome these limitations. Specifically, we design a lightweight multi-scale invertible neural network, which bijectively maps the input image into multi-scale latent representations. To improve the compression efficiency, a multi-scale spatial-channel context model with extended gain units is devised to estimate the entropy of the latent representation from high to low levels. Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods, and remains competitive with recent multi-model approaches. Notably, our method is the first learned image compression solution that outperforms VVC across a very wide range of bit rates using a single model, especially at high bit rates. The source code is available at https://github.com/hytu99/MSINN-VRLIC.