Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization
This work addresses the standardization of JPEG-AI for improved image compression, but it is incremental as it builds on existing models by adapting strategies from VVC intra.
The paper tackles the problem of optimizing bit distribution in the JPEG-AI neural network-based image compression codec, revealing that VVC intra has a more adaptable structure and proposing a spatial bit allocation method that improves JPEG-AI's performance by up to 0.45 dB in PSNR-Y.
Currently, there is a high demand for neural network-based image compression codecs. These codecs employ non-linear transforms to create compact bit representations and facilitate faster coding speeds on devices compared to the hand-crafted transforms used in classical frameworks. The scientific and industrial communities are highly interested in these properties, leading to the standardization effort of JPEG-AI. The JPEG-AI verification model has been released and is currently under development for standardization. Utilizing neural networks, it can outperform the classic codec VVC intra by over 10% BD-rate operating at base operation point. Researchers attribute this success to the flexible bit distribution in the spatial domain, in contrast to VVC intra's anchor that is generated with a constant quality point. However, our study reveals that VVC intra displays a more adaptable bit distribution structure through the implementation of various block sizes. As a result of our observations, we have proposed a spatial bit allocation method to optimize the JPEG-AI verification model's bit distribution and enhance the visual quality. Furthermore, by applying the VVC bit distribution strategy, the objective performance of JPEG-AI verification mode can be further improved, resulting in a maximum gain of 0.45 dB in PSNR-Y.