Neural Nearest Neighbors Networks

NeurIPS 2018 • Tobias Plötz • Stefan Roth

Non-local methods exploiting the self-similarity of natural signals have been well studied, for example in image analysis and restoration. Existing approaches, however, rely on k-nearest neighbors (KNN) matching in a fixed feature space... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Grayscale Image Denoising BSD68 sigma25 N3Net PSNR 29.3 # 4
Grayscale Image Denoising BSD68 sigma50 N3Net PSNR 26.39 # 5
Grayscale Image Denoising BSD68 sigma70 N3Net PSNR 25.14 # 1
Grayscale Image Denoising Set12 sigma25 N3Net PSNR 30.55 # 3
Grayscale Image Denoising Set12 sigma50 N3Net PSNR 27.43 # 4
Grayscale Image Denoising Set12 sigma70 N3Net PSNR 25.9 # 1
Image Super-Resolution Set5 - 2x upscaling N3Net PSNR 37.57 # 13
Image Super-Resolution Set5 - 3x upscaling N3Net PSNR 33.84 # 8
Image Super-Resolution Set5 - 4x upscaling N3Net PSNR 31.5 # 26
Grayscale Image Denoising Urban100 sigma25 N3Net PSNR 30.19 # 4
SSIM 0.892 # 1
Grayscale Image Denoising Urban100 sigma50 N3Net PSNR 26.82 # 5
Grayscale Image Denoising Urban100 sigma70 N3Net PSNR 25.15 # 2