SeGAN: Segmenting and Generating the Invisible
This addresses scene understanding and object manipulation by improving occlusion handling, though it appears incremental as it builds on existing segmentation and generation methods.
The paper tackles the problem of completing the appearance of occluded objects by jointly segmenting and generating invisible parts, showing that SeGAN outperforms state-of-the-art segmentation baselines and can generalize to natural images.
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.