Amodal Instance Segmentation

Abstract

We consider the problem of amodal instance segmentation, the objective of which is to predict the region encompassing both visible and occluded parts of each object. Thus far, the lack of publicly available amodal segmentation annotations has stymied the development of amodal segmentation methods. In this paper, we sidestep this issue by relying solely on standard modal instance segmentation annotations to train our model. The result is a new method for amodal instance segmentation, which represents the first such method to the best of our knowledge. We demonstrate the proposed method's effectiveness both qualitatively and quantitatively.

23 pages, 14 figures; European Conference on Computer Vision (ECCV), 2016

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Instance-aware Semantic Segmentation via Multi-task Network Cascades

Cited by in corpus (8)

• CityPersons: A Diverse Dataset for Pedestrian Detection
• Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
• Visual Concepts and Compositional Voting
• Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning
• Oriented Boxes for Accurate Instance Segmentation
• SeGAN: Segmenting and Generating the Invisible
• Self-Supervised Scene De-occlusion
• DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion