SROBB: Targeted Perceptual Loss for Single Image Super-Resolution

Rad M. S., Bozorgtabar B., Marti U., Basler M., Ekenel H. K., Thiran J.

IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, South Korea, 27 October - 02 November 2019, pp.2710-2719 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iccv.2019.00280
  • City: Seoul
  • Country: South Korea
  • Page Numbers: pp.2710-2719
  • Istanbul Technical University Affiliated: Yes


By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions generate near-photorealistic results, their capability is limited, since they estimate the reconstruction error for an entire image in the same way, without considering any semantic information. In this paper, we propose a novel method to benefit from perceptual loss in a more objective way. We optimize a deep network-based decoder with a targeted objective function that penalizes images at different semantic levels using the corresponding terms. In particular, the proposed method leverages our proposed OBB (Object, Background and Boundary) labels, generated from segmentation labels, to estimate a suitable perceptual loss for boundaries, while considering texture similarity for backgrounds. We show that our proposed approach results in more realistic textures and sharper edges, and outperforms other state-of-the-art algorithms in terms of both qualitative results on standard benchmarks and results of extensive user studies.