DPICT: Deep Progressive Image Compression Using Trit-Planes
release_3x2qnevwqva4pi7namjbtxu63m
by
Jae-Han Lee, Seungmin Jeon, Kwang Pyo Choi, Youngo Park, Chang-Su Kim
2021
Abstract
We propose the deep progressive image compression using trit-planes (DPICT)
algorithm, which is the first learning-based codec supporting fine granular
scalability (FGS). First, we transform an image into a latent tensor using an
analysis network. Then, we represent the latent tensor in ternary digits
(trits) and encode it into a compressed bitstream trit-plane by trit-plane in
the decreasing order of significance. Moreover, within each trit-plane, we sort
the trits according to their rate-distortion priorities and transmit more
important information first. Since the compression network is less optimized
for the cases of using fewer trit-planes, we develop a postprocessing network
for refining reconstructed images at low rates. Experimental results show that
DPICT outperforms conventional progressive codecs significantly, while enabling
FGS transmission.
In text/plain
format
Archived Files and Locations
application/pdf 2.7 MB
file_33ynlpcc2rd5dm5q6nhynr33me
|
arxiv.org (repository) web.archive.org (webarchive) |
2112.06334v1
access all versions, variants, and formats of this works (eg, pre-prints)