SeGAN: Segmenting and Generating the Invisible
Citations Over TimeTop 10% of 2018 papers
Abstract
Objects often occlude each other in scenes; Inferring their appearance beyond their visible parts plays an important role in scene understanding, depth estimation, object interaction and manipulation. In this paper, we study the challenging problem of completing the appearance of occluded objects. Doing so requires knowing which pixels to paint (segmenting the invisible parts of objects) and what color to paint them (generating the invisible parts). Our proposed novel solution, SeGAN, jointly optimizes for both segmentation and generation of the invisible parts of objects. Our experimental results show that: (a) SeGAN can learn to generate the appearance of the occluded parts of objects; (b) SeGAN outperforms state-of-the-art segmentation baselines for the invisible parts of objects; (c) trained on synthetic photo realistic images, SeGAN can reliably segment natural images; (d) by reasoning about occluder-occludee relations, our method can infer depth layering.
Related Papers
- → Object segmentation using stereo images(2004)15 cited
- → Segmentation of moving images by the human visual system(1997)7 cited
- → Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation(2016)30 cited
- → Towards Object Detection from Motion(2019)1 cited
- Foreground and shadow detection for video surveillance(2009)