论文标题
MVMO：用于宽基线多视图语义细分的多对象数据集
MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation
论文作者
论文摘要
我们提供MVMO（多视图，多对象数据集）：一个116,000场景的合成数据集，其中包含10个不同类别的随机放置对象，并从上半球的25个相机位置捕获。 MVMO包括光真逼真的，路径跟踪的图像渲染，以及每个观点的语义分割地面真相。与现有的多视图数据集不同，MVMO具有摄像机和高密度对象之间的宽基线，这会导致较大的差异，沉重的遮挡和观点依赖的对象外观。单个视图语义分割受到可能受益于其他观点的自我和对象的阻塞。因此，我们预计MVMO将推进多视图语义分割和跨视图语义转移的研究。我们还提供基准，这些基线表明在此类领域需要新的研究来利用多视图设置的互补信息。
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.
