JPEG-AI
PulseAugur coverage of JPEG-AI — every cluster mentioning JPEG-AI across labs, papers, and developer communities, ranked by signal.
-
New research benchmarks face compression codecs for identity preservation
A new research paper explores the challenge of compressing face images to under 1 kilobyte while preserving identity for applications like identity documents and biometric verification. The study benchmarks ten general …
-
New compression techniques aim to fit face recognition images into 1024 bytes
This research paper explores methods to compress facial images to under 1024 bytes for use in temporary travel documents, enabling machine readability via 2D barcodes. The study evaluates various compression formats inc…
-
New compression methods aim for sub-1KB face images in travel documents
A new research paper explores methods for compressing facial images to under 1024 bytes for use in temporary travel documents, aiming to enable machine readability via 2D barcodes. The study evaluates various compressio…
-
Apple researchers unveil learned image codec with 3x bitrate savings and fast mobile speeds
Researchers have developed a new learned image codec that significantly improves the trade-off between perceptual quality and runtime speed. Through a comprehensive study of modeling choices and performance-aware neural…