Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification

19 Nov 2016 Woong Bae Jaejun Yoo Jong Chul Ye

The latest deep learning approaches perform better than the state-of-the-art signal processing approaches in various image restoration tasks. However, if an image contains many patterns and structures, the performance of these CNNs is still inferior... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Super-Resolution BSD100 - 4x upscaling Manifold Simplification PSNR 27.66 # 17
SSIM 0.7380 # 20
Color Image Denoising CBSD68 sigma50 DnCNN PSNR 28.01 # 3
Image Super-Resolution Set14 - 4x upscaling Manifold Simplification PSNR 28.80 # 17
SSIM 0.7856 # 21
Image Super-Resolution Set5 - 4x upscaling Manifold Simplification PSNR 32.23 # 19
SSIM 0.8952 # 21
Image Super-Resolution Urban100 - 4x upscaling Manifold Simplification PSNR 26.42 # 17
SSIM 0.7940 # 17

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet