Quality and Complexity Assessment of Learning-Based Image Compression Solutions
This incremental analysis assesses the trade-offs in quality and complexity for image compression, relevant for researchers and practitioners in multimedia and AI.
This work analyzed state-of-the-art learning-based image compression techniques, comparing 8 models with BPG and JPEG2000 on the KODAK dataset, finding that learning-based models improved quality over JPEG2000 at lower bitrates, with JPEG2000 being faster by up to 30x in decompression.
This work presents an analysis of state-of-the-art learning-based image compression techniques. We compare 8 models available in the Tensorflow Compression package in terms of visual quality metrics and processing time, using the KODAK data set. The results are compared with the Better Portable Graphics (BPG) and the JPEG2000 codecs. Results show that JPEG2000 has the lowest execution times compared with the fastest learning-based model, with a speedup of 1.46x in compression and 30x in decompression. However, the learning-based models achieved improvements over JPEG2000 in terms of quality, specially for lower bitrates. Our findings also show that BPG is more efficient in terms of PSNR, but the learning models are better for other quality metrics, and sometimes even faster. The results indicate that learning-based techniques are promising solutions towards a future mainstream compression method.