Checkerboard Context Model for Efficient Learned Image Compression
This addresses a computational bottleneck for researchers and practitioners in image compression, enabling faster decoding without sacrificing quality, though it is an incremental improvement on existing context models.
The paper tackles the problem of slow decoding in learned image compression due to sequential autoregressive models by proposing a parallelizable checkerboard context model (CCM), which speeds up decoding by over 40 times while maintaining nearly the same rate-distortion performance.
For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.