Chris Pollett > Students >

    ( Print View)



    [CS 297 Proposal]

    [Deliverable 1]

    [Deliverable 2]

    [Deliverable 3]

    [Deliverable 4]

    [End to End Image Compression - PDF]

    [Image file formats - PDF]

    [DeepN-JPEG - PDF]

    [Image compression using RNN - PDF]

    [CS 297 Report - PDF]

    [CS 298 Proposal]

    [CS 298 report]

CS297 Proposal

Image compression using neural networks

Kunal Deshmukh (

Advisor: Dr. Chris Pollett


Image compression is one of the most studied problems in computer science. Traditionally, lossless and lossy image compression algorithms such as Run-length encoding or Transform coding is used for this purpose.
Neural nets are used widely for image classification and detection problems. When a neural network is trained on images, some information about those images gets stored in the neural network in the form of network parameters such as weights while some information is passed on to next layers in a convoluted representation. This project aims to reconstruct an image using this representation and model parameters. A new architecture for image compression needs to be developed for this purpose. Further, the quality of an image thus obtained, can be enhanced by using Generative Adversarial Network (GANs).


Week 1: Aug 28 - Sept4 Kickoff meeting with Dr. Pollett
Week 2: Sept 5 - Sept 11Read end to end image compression using neural network [3] .
Week 3: Sept 12 - Sept 18Deliverable 1 : Implement end to end image compression[3] architecture in tensorflow
Week 4: Sept 19 - Sept 25Explore convoluted representation and perform experiments on Deliverable 1
Week 5: Sept 26 - Oct 2Work on Deliverable 2
Week 6: Oct 3 - Oct 9Deliverable 2 : Implement Single Image Super-Resolution(SISR) using GAN[4].
Week 7: Oct 10 - Oct 16Explore denoising and sparse autoencoders
Week 7: Oct 10 - Oct 16Study popular image file formats
Week 8: Oct 17 - Oct 23Read paper: Real-Time Adaptive Image Compression
Week 9: Oct 24 - Oct 30Explore Generative adversarial network
Week 10: Oct 31 - Nov 6 Deliverable 3 : Modify Deliverable - 1 to run on ImageNet dataset. Find SSIM, PSNR matrices.
Week 11: Nov 7 - Nov 13Learn how to measure a loss in image. Objective and Subjective methods to evaluate Image quality.
Week 12: Nov 14 - Nov 20Work on Deliverable 4
Week 13: Nov 21 - Nov 27Deliverable 4 :
Week 14: Nov 28 - Dec 4Implement "Full resolution image compression using Recurrent Neural Networks" [2]
Week 15: Dec 5 - Dec 11Work on Deliverable 5
Week 16: Dec 12 - Dec 18Deliverable 5 : Complete CS 297 final report


The full project will be done when CS298 is completed. The following will be done by the end of CS297:

  1. Deliverable 1 : Implement end to end image compression[4] architecture in tensorflow.
  2. Deliverable 2: Implement SISR using GAN.
  3. Write a code in Keras for GAN to classify zener card images.
  4. Find suitable pre-trained model from model zoo and train to identify car in imagenet dataset.
  5. Complete CS 297 final report.


[1] Rippel Oren, Bourdev Lubomir (May 2017). Real-Time Adaptive Image Compression. Published at ICML 2017.Sydney, Austrelia. arxiv e-archive.

[2] Toderici George, et al. (July 2017). Full Resolution Image Compression with Recurrent Neural Networks. Google Inc. Google research

[3] Jiang Feng, et al. (August 2017). An End-to-End Compression Framework Based on Convolutional Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology. Harbin, China. arxiv e-archive.

[4] Ledig Christian, et al. (May 2017) .Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii. arxiv e-archive