Compression performance¶

Reproduce our current best results¶

We provide already encoded files as bitstreams in results/<configuration>/<dataset_name>/

  • <configuration> can be image

  • <dataset_name> can be kodak, clic20-pro-valid, jvet.

These bitstreams allow to reproduce the results stated above qnd reflect the current best rate-distortion results achievable with Cool-chic.

For each dataset, a script decodes all the bitstreams.

(venv) python results/decode_one_dataset.py <configuration> <dataset_name> # Can take a few minutes

The file results/<configuration>/<dataset_name>/results.tsv provides the results that should be obtained.

Image compression¶

Image compression performance are presented on the kodak dataset, clic20-pro-valid and jvet datasets.

The following table sums up the compression performance obtained by Cool-chic 3.3 against different anchors.

Dataset

vs. Cool-chic 3.1 [%]

vs. C3, Kim et al. [%]

vs. HEVC (HM 16.20) [%]

vs. VVC (VTM 19.1) [%]

Avg decoder complexity [MAC / pixel]

Avg decoding time [ms]

kodak

-1.9

-3.4

-16.4

+4.5

1880

96

clic20-pro-valid

-4.2

-1.0

-24.8

-1.9

1907

364

jvet B

-7.2

/

-10.8

19.5

1803

260

jvet C

-2.4

/

-15.0

10.7

1942

75

jvet D

-1.3

/

-11.2

11.1

1086

21

jvet E

-9.0

/

-2.5

32.7

1814

106

jvet F

-3.1

/

-32.0

20.3

2201

152

We also present the performance-complexity continuum on Kodak. The different configurations (VLOP, LOP, MOP, HOP) are obtained using the configuration files detailed in the decoder documentation. For the MIX configuration, we pick the best configuration out of the 4 available ones for each image.

Kodak¶

We show below the rate-distortion performance on Kodak:

Kodak rd results Kodak performance-complexity Kodak performance-decoding-time

CLIC20 Pro Valid¶

CLIC20 rd results CLIC20 performance-complexity CLIC20 performance-decoding-time

JVET Class B¶

JVET class B rd results JVET class B performance-complexity JVET class B performance-decoding-time