| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0569938 |
| utime |
20230316110705.5 |
| mtime |
20230313235959.9 |
| SCOPUS |
85134982515 |
| WOS |
000867754200066 |
| DOI |
10.1109/CVPR52688.2022.00074 |
| title
(primary) (eng) |
SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention |
| specification |
| page_count |
10 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0570015 |
| ISBN |
978-1-6654-6946-3 |
| ISSN |
1063-6919 |
| title
|
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) |
| page_num |
661-670 |
| publisher |
| place |
Piscataway |
| name |
IEEE |
| year |
2022 |
|
|
| keyword |
Deep learning architectures and techniques |
| keyword |
Image and video synthesis and generation |
| keyword |
Machine learning |
| author
(primary) |
| ARLID |
cav_un_auth*0447356 |
| name1 |
Wödlinger |
| name2 |
M. |
| country |
AT |
|
| author
|
| ARLID |
cav_un_auth*0293863 |
| name1 |
Kotera |
| name2 |
Jan |
| institution |
UTIA-B |
| full_dept (cz) |
Zpracování obrazové informace |
| full_dept |
Department of Image Processing |
| department (cz) |
ZOI |
| department |
ZOI |
| full_dept |
Department of Image Processing |
| country |
CZ |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0447357 |
| name1 |
Sablatnig |
| name2 |
R. |
| country |
AT |
|
| source |
|
| cas_special |
| abstract
(eng) |
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. |
| action |
| ARLID |
cav_un_auth*0447358 |
| name |
Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022) |
| dates |
20220619 |
| mrcbC20-s |
20220624 |
| place |
New Orleans |
| country |
US |
|
| RIV |
JC |
| FORD0 |
10000 |
| FORD1 |
10200 |
| FORD2 |
10201 |
| reportyear |
2023 |
| num_of_auth |
3 |
| presentation_type |
PR |
| inst_support |
RVO:67985556 |
| permalink |
https://hdl.handle.net/11104/0341356 |
| cooperation |
| ARLID |
cav_un_auth*0301586 |
| name |
Technische Universität Wien |
| institution |
TUW |
| country |
AT |
|
| confidential |
S |
| mrcbC86 |
n.a. Proceedings Paper Computer Science Artificial Intelligence|Imaging Science Photographic Technology |
| arlyear |
2022 |
| mrcbU14 |
85134982515 SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
000867754200066 WOS |
| mrcbU63 |
cav_un_epca*0570015 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) IEEE 2022 Piscataway 661 670 978-1-6654-6946-3 IEEE Conference on Computer Vision and Pattern Recognition 1063-6919 |
|