TY  - CONF
AU  - Aitor Alvarez-Gila
AU  - Joost Van de Weijer
AU  - Yaxing Wang
AU  - Estibaliz Garrote
A2  - ICIP
PY  - 2022//
TI  - MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation
BT  - 29th IEEE International Conference on Image Processing
KW  - multi-view
KW  - cross-view
KW  - semantic segmentation
KW  - synthetic dataset
N2  - 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 1 .
UR  - https://ieeexplore.ieee.org/document/9897955
L1  - http://158.109.8.37/files/AWW2022.pdf
UR  - http://dx.doi.org/10.1109/ICIP46576.2022.9897955
N1  - LAMP
ID  - Aitor Alvarez-Gila2022
ER  -