Index Network

11 Aug 2019Hao LuYutong DaiChunhua ShenSongcen Xu

We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover boundary details considerably better than other upsampling operators such as bilinear interpolation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Grayscale Image Denoising BSD68 sigma15 Index Network PSNR 31.23 # 8
Grayscale Image Denoising BSD68 sigma25 Index Network PSNR 29.06 # 8
Grayscale Image Denoising BSD68 sigma50 Index Network PSNR 26.34 # 7
Monocular Depth Estimation NYU-Depth V2 Index Network RMSE 0.565 # 14
Grayscale Image Denoising Set12 sigma15 Index Network PSNR 32.82 # 4
Grayscale Image Denoising Set12 sigma30 Index Network PSNR 30.43 # 2
Grayscale Image Denoising Set12 sigma50 Index Network PSNR 27.29 # 5
Scene Segmentation SUN-RGBD Index Network Mean IoU 33.48 # 1

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