Joint Photographic Expert Group
The Joint Photographic Experts Group (JPEG) standard, while foundational for image compression, is the subject of ongoing research aimed at improving its efficiency, robustness, and integration with modern deep learning techniques. Current research focuses on developing learning-based codecs that outperform traditional methods in terms of compression ratios and image quality, particularly for specialized applications like fingerprint storage and point cloud representation. These advancements leverage architectures such as transformers and convolutional neural networks, often operating directly on compressed data to minimize computational overhead. The resulting improvements have significant implications for various fields, including digital image processing, computer vision, and data storage.
Papers
Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model
Panqi Jia, A. Burakhan Koyuncu, Jue Mao, Ze Cui, Yi Ma, Tiansheng Guo, Timofey Solovyev, Alexander Karabutov, Yin Zhao, Jing Wang, Elena Alshina, Andre Kaup
Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization
Panqi Jia, Jue Mao, Esin Koyuncu, A. Burakhan Koyuncu, Timofey Solovyev, Alexander Karabutov, Yin Zhao, Elena Alshina, Andre Kaup