Edge-Informed Single Image Super-Resolution

11 Sep 2019  ·  Kamyar Nazeri, Harrish Thasarathan, Mehran Ebrahimi ·

The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR problem is reformulated as an image inpainting task. We use a two-stage inpainting model as a baseline for super-resolution and show its effectiveness for different scale factors (x2, x4, x8) compared to basic interpolation schemes. This model is trained using a joint optimization of image contents (texture and color) and structures (edges). Quantitative and qualitative comparisons are included and the proposed model is compared with current state-of-the-art techniques. We show that our method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image. Code and models available at: https://github.com/knazeri/edge-informed-sisr

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution BSD100 - 4x upscaling Edge-informed SR PSNR 24.25 # 59
SSIM 0.851 # 1
Image Super-Resolution Celeb-HQ 4x upscaling Edge-informed SR PSNR 28.23 # 1
SSIM 0.912 # 1
Image Super-Resolution Set14 - 4x upscaling Edge-informed SR PSNR 25.19 # 61
SSIM 0.894 # 1
Image Super-Resolution Set5 - 4x upscaling Edge-informed SR PSNR 28.59 # 66
SSIM 0.965 # 1


No methods listed for this paper. Add relevant methods here