MVMO: A MULTI-OBJECT DATASET FOR WIDE BASELINE MULTI-VIEW SEMANTIC SEGMENTATION

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).

Automated summary

MVMO is a synthetic dataset with high object density and wide camera baselines, enabling research in multi-view semantic segmentation and cross-view semantic transfer. New research is needed to utilize the information from multi-view setups effectively.