Presentation is loading. Please wait.

Presentation is loading. Please wait.

Deep screen image crop and enhance

Similar presentations


Presentation on theme: "Deep screen image crop and enhance"— Presentation transcript:

1 Deep screen image crop and enhance
Week 2 (Aaron Ott, Amir Mazaheri)

2 Problem We have taken a photo of an image, and we want the original image. This can be broken into 2 parts: Image Detector/Cropper Image Enhancer

3 Enhancer - Pretrained EDSR (trained on DIV2K)
- Pretrained EDSR (trained on DIV2K) - Modified form of Resnet - Actually scales up the image 4x Lim, Son, Kim, Nah, Lee. “Enhanced Deep Residual Networks for Single Image Super-Resolution”. 10 July 2017

4 Combining the Cropper and Enhancer
Had to use lambda functions and AveragePooling2D to get the Enhancer to properly work with the Cropper Loss Functions: - Trained Cropper on VGG+CosineProximity - Trained Enhancer on VGG+MSE

5 Last Week (Cropper) Metrics: PSNR: 11.1903 SSIM: 0.4254
MSE: Last Week (Cropper) Cropper using a Spatial Transformation Network Input Output Actual

6 This Week (Cropper + Enhancer)
Metrics: PSNR: SSIM: MSE: This Week (Cropper + Enhancer) Input Output Actual

7 Metrics Compared Model \ Metric PSNR SSIM MSE Cropper 11.1903 0.4254
0.0796 Cropper + Enhancer 0.4807 0.0316

8 Shortcomings of PSNR, SSIM, and MSE
Model \ Metric PSNR SSIM MSE Cropper 0.4254 0.0796 Cropper + Enhancer 0.4807 0.0316 Cropper + Enhancer w/ MSE Loss 0.5314 0.0166

9 Shortcomings of PSNR, SSIM, and MSE
Metrics: PSNR: SSIM: MSE: Input Output Loss Functions VGG + Cosine Proximity MSE Actual

10 Next Week Create and refine GAN architecture
Refine EDSR or try a different SISR (WDSR)


Download ppt "Deep screen image crop and enhance"

Similar presentations


Ads by Google