SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation – A Synthetic Dataset and Baselines

We introduce SAIL-VOS (Semantic Amodal Instance Level Video Object Segmentation), a new dataset aiming to stimulate semantic amodal segmentation research. Humans can effortlessly recognize partially occluded objects and reliably estimate their spatial extent beyond the visible. However, few modern computer vision techniques are capable of reasoning about occluded parts of an object. This is partly due to the fact that very few image datasets and no video dataset exist which permit development of those methods. To address this issue, we present a synthetic dataset extracted from the photo-realistic game GTA-V. Each frame is accompanied with densely annotated, pixel-accurate visible and amodal segmentation masks with semantic labels. More than 1.8M objects are annotated resulting in 100 times more annotations than existing datasets. We demonstrate the challenges of the dataset by quantifying the performance of several baselines. Data and additional material is available at http://sailvos.web.illinois.edu.

1. Introduction

Semantic amodal instance level video object segmentation (SAIL-VOS), i.e., semantically segmenting individual objects in videos even under occlusion, is an important problem for sophisticated occlusion reasoning, depth ordering, and object size prediction. Particularly the temporal sequence provided by a densely and semantically labeled video dataset is increasingly important since it enables assessment of temporal reasoning and evaluation of methods which anticipate the behavior of objects and humans.