TY - GEN
T1 - MVMO
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
AU - Alvarez-Gila, Aitor
AU - van de Weijer, Joost
AU - Wang, Yaxing
AU - Garrote, Estibaliz
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
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.
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.
KW - cross-view
KW - multi-view
KW - semantic segmentation
KW - synthetic dataset
UR - http://www.scopus.com/inward/record.url?scp=85146662314&partnerID=8YFLogxK
U2 - 10.1109/ICIP46576.2022.9897955
DO - 10.1109/ICIP46576.2022.9897955
M3 - Conference contribution
AN - SCOPUS:85146662314
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1166
EP - 1170
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - IEEE Computer Society
Y2 - 16 October 2022 through 19 October 2022
ER -