Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding

arXiv:2403.07320v1 Announce Type: cross
Abstract: Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal in a one-shot sense on certain sources, we show that it is highly sub-optimal on i.i.d. sequences, and in fact always recovers scalar quantization of the …

abstract arxiv coding complexity compression cs.it cs.lg design designing eess.sp entropy good integers lattice low math.it neural compression performance progress rate type vector