RT Conference Proceedings
T1 MVMO: 												A MULTI-OBJECT DATASET FOR WIDE BASELINE MULTI-VIEW SEMANTIC SEGMENTATION
A1 Alvarez-Gila, Aitor
A1 van de Weijer, Joost
A1 Wang, Yaxing
A1 Garrote, Estibaliz
AB We present MVMO (Multi-View, Multi-Object dataset): a synthetic dataset of 116, 000 scenes containing randomly placed objects of 10 distinct classes and captured from 25 camera locations in the upper hemisphere. MVMO comprises photorealistic, path-traced image renders, together with semantic segmentation ground truth for every view. Unlike existing multi-view datasets, MVMO features wide baselines between cameras and high density of objects, which lead to large disparities, heavy occlusions and view-dependent object appearance. Single view semantic segmentation is hindered by self and inter-object occlusions that could benefit from additional viewpoints. Therefore, we expect that MVMO will propel research in multi-view semantic segmentation and cross-view semantic transfer. We also provide baselines that show that new research is needed in such fields to exploit the complementary information of multi-view setups.
PB IEEE Computer Society
SN 9781665496209
SN 1522-4880
YR 2022
FD 2022
LK https://hdl.handle.net/11556/2498
UL https://hdl.handle.net/11556/2498
LA eng
NO Alvarez-Gila , A , van de Weijer , J , Wang , Y & Garrote , E 2022 , MVMO : A MULTI-OBJECT DATASET FOR WIDE BASELINE MULTI-VIEW SEMANTIC SEGMENTATION . in 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings . Proceedings - International Conference on Image Processing, ICIP , IEEE Computer Society , pp. 1166-1170 , 29th IEEE International Conference on Image Processing, ICIP 2022 , Bordeaux , France , 16/10/22 . https://doi.org/10.1109/ICIP46576.2022.9897955
NO conference
NO Publisher Copyright: © 2022 IEEE.
NO ∗This work is part of the projects 3KIA (KK-2020/00049) and BasqNet (KK-2021/00014), funded by the SPRI-Basque Government-ELKARTEK. †Government of Spain-funded project PID2019-104174GB-I00/AEI/10.13039/501100011033 1Code and dataset: https://aitorshuffle.github.io/projects/mvmo/
DS TECNALIA Publications
RD 26 jul 2024