arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.10348cs.CV
收藏

结构修复

Structural inpainting

Technicolor(特艺集团)

Huy V. Vo, Ngoc Q. K. Duong, Patrick Perez

摘要:

场景无关的视觉修复仍然是非常具有挑战性的,尽管在基于补丁的方法的进展。最近,Pathak等人在2016年引入了卷积“上下文编码器”(CE),用于通过图像完成任务进行无监督特征学习。在对抗训练的额外帮助下,CE被证明是一种很有前途的工具,可以在真正的修复问题中完成复杂的结构。在本文中,我们建议通过依赖训练时的感知重建损失来进一步推动这一关键能力。我们展示了各种各样的视觉场景的优点的结构修复的方法,并确认它通过用户研究。结合Yang等人2016年使用神经补丁进行的基于优化的改进,我们的上下文编码器为无先验视觉修复开辟了新的机会。

英文摘要:

Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image completion tasks. With the additional help of adversarial training, CEs turned out to be a promising tool to complete complex structures in real inpainting problems. In the present paper we propose to push further this key ability by relying on perceptual reconstruction losses at training time. We show on a wide variety of visual scenes the merit of the approach for structural inpainting, and confirm it through a user study. Combined with the optimization-based refinement of Yang et al. 2016 with neural patches, our context encoder opens up new opportunities for prior-free visual inpainting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑