Deep screen image crop and enhance

Slides:



Advertisements
Similar presentations
A brief review of non-neural-network approaches to deep learning
Advertisements

CAPTCHA solving Tianhui Cai Period 3. CAPTCHAs Completely Automated Public Turing tests to tell Computers and Humans Apart Determines whether a user is.
1 End-to-End Learning for Automatic Cell Phenotyping Paolo Emilio Barbano, Koray Kavukcuoglu, Marco Scoffier, Yann LeCun April 26, 2006.
Logan Lebanoff Mentor: Haroon Idrees
Deep Residual Learning for Image Recognition
Combining Neural Networks and Context-Driven Search for On- Line, Printed Handwriting Recognition in the Newton Larry S. Yaeger, Brandn J. Web, and Richard.
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Wenchi MA CV Group EECS,KU 03/20/2017
Convolutional Sequence to Sequence Learning
Learning to Compare Image Patches via Convolutional Neural Networks
Analysis of Sparse Convolutional Neural Networks
Deep Residual Networks
Summary of “Efficient Deep Learning for Stereo Matching”
Data Mining, Neural Network and Genetic Programming
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
The Problem: Classification
Textual Video Prediction Week 2
Understanding and Predicting Image Memorability at a Large Scale
Matt Gormley Lecture 16 October 24, 2016
Inception and Residual Architecture in Deep Convolutional Networks
Intelligent Information System Lab
LARS Background Reference Paper: Reference Patch in Intel Caffe
Synthesis of X-ray Projections via Deep Learning
Super-resolution Image Reconstruction
Single Image Super-Resolution
Efficient Deep Model for Monocular Road Segmentation
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Presenter: Hajar Emami
Deep Learning Convoluted Neural Networks Part 2 11/13/
By: Kevin Yu Ph.D. in Computer Engineering
Layer-wise Performance Bottleneck Analysis of Deep Neural Networks
Bird-species Recognition Using Convolutional Neural Network
Visual Question Generation
Face Recognition with Deep Learning Method
Image Classification.
Deep CNN of JPEG 2000 電信所R 林俊廷.
Road Traffic Sign Recognition
Tips for Training Deep Network
Basics of Deep Learning No Math Required
Multilayer Perceptron & Backpropagation
A Proposal Defense On Deep Residual Network For Face Recognition Presented By SAGAR MISHRA MECE
Lecture: Deep Convolutional Neural Networks
Use 3D Convolutional Neural Network to Inspect Solder Ball Defects
ML – Lecture 3B Deep NN.
Transforming Graphs of Functions
Solve the equation: 6 x - 2 = 7 x + 7 Select the correct answer.
边缘检测年度进展概述 Ming-Ming Cheng Media Computing Lab, Nankai University
Abnormally Detection
Deep Object Co-Segmentation
Natalie Lang Tomer Malach
Textual Video Prediction
Batch Normalization.
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
What's New in eCognition 9
Weeks 1 and 2 Aaron Ott.
Deep screen image crop and enhance
End-to-End Facial Alignment and Recognition
CRCV REU 2019 Kara Schatz.
Appearance Transformer (AT)
Week 3 Volodymyr Bobyr.
Deep screen image crop and enhance
Self-Supervised Cross-View Action Synthesis
Deep screen image crop and enhance
CRCV REU 2019 Aaron Honculada.
Deep screen image crop and enhance
Deep screen image crop and enhance
Directional Occlusion with Neural Network
20 November 2019 Output maps Normal Diffuse Roughness Specular
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Deep CNN for breast cancer histology Image Analysis
Presentation transcript:

Deep screen image crop and enhance Week 8 (Aaron Ott, Amir Mazaheri)

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

Cropper Uses a frozen VGG-19 model to get feature map Applies convolutions, normalizations, and activations Final dense layer creates 6-number theta value for affine transformation STN takes input image and applies affine transformation

Enhancer Pretrained EDSR (trained on DIV2K) Modified form of Resnet https://github.com/krasserm/super-resolution Pretrained EDSR (trained on DIV2K) Modified form of Resnet Uses modified residual block, which excludes batch normalization and final ReLU layer 16 Residual blocks Subpixel Conv2D layers for upscaling the image Scales the image 4x Lim, Son, Kim, Nah, Lee. “Enhanced Deep Residual Networks for Single Image Super-Resolution”. 10 July 2017

Combined Cropper and Enhancer Trained with 2 outputs and 2 Loss Functions: - Trained Cropper on VGG + Cosine Proximity (Inception Loss) - Trained Enhancer on VGG + MSE

Results Metric\Model Cropper Cropper & Enhancer PSNR 11.1903 16.2060 SSIM 0.4254 0.4909 MSE 0.0796 0.0281 MOS 2.6143 2.8857 Results Cropper & Enhancer Input Cropper Actual

Synthetic Dataset Problem: There is no existing dataset to use when solving this problem, and taking pictures takes too much time Solution: Automatically generate images with various transformations over various backgrounds - Current problems: sometimes image edges get cut out, difficult to get full variety of possible images, doesn’t yet account for discoloration or image noise, dataset only includes birds http://www.vision.caltech.edu/visipedia/CUB-200.html, http://places2.csail.mit.edu/download.html

Synthetic Dataset Results Original Cropper + Enhancer Cropper w/ SD Cropper w/ 2 SDs Original Cropper Input Truth * Note: Used separate validation data set that none of the networks had been trained on. PSNR 12.5088 12.3735 12.6044 12.8537 SSIM 0.3366 0.3335 0.3450 0.3437 MSE 0.0609 0.0586 0.0578

Projective Transformation Issues It turns out the STN we were using cannot handle projective transformations (it doesn’t take in account a z axis in any of the equations) After searching through many implementations, we could not find a STN implementation that allowed for projective transformations. Existing projective transformation functions don’t allow for passing gradients. Workarounds?

New Objective: Can we give our network an input image with multiple images, tell it which class of image to retrieve, and retrieve the correct image? 1 - Balloon 2 - Birdhouse 4 – Persian Cat 3 - French Bulldog

Other additions to our network: Attention module – Identify area of the photo where the image specified is Multiple Croppers – Try to progressively crop the image to get better and better crops

Next Week Continue running experiments Get paper written