SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F22%3A00569938" target="_blank" >RIV/67985556:_____/22:00569938 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/CVPR52688.2022.00074" target="_blank" >http://dx.doi.org/10.1109/CVPR52688.2022.00074</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52688.2022.00074" target="_blank" >10.1109/CVPR52688.2022.00074</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention

Popis výsledku v původním jazyce

We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.

Název v anglickém jazyce

SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention

Popis výsledku anglicky

We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)

ISBN

978-1-6654-6946-3

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

10

Strana od-do

661-670

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

New Orleans

Datum konání akce

19. 6. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000867754200066