CS194-26 Computational Photography, Image Processing, and Computer vision

Modernizing the Prokudin-Gorskii Photo Collection

This was the first project for my computational photography class with professor Alexi Efros. It involved aligning and enhancing the Prokudin-Gorskii photo collection.

Read More

Fun with Frequencies and Gradients

The project was all about using the gradient domain. Ranging from edge detection convolution filters to multiresolution blending.

Read More

Face Morphing

In this project, I create some face merging and averaging and then apply machine learning to automate the process.

Read More

Deep Networks for Computer Vision

The first part of this project used a CNN to classify the fasion mnist set. The Second used a U-Net style architecture to segment images of building dataset.

Read More

CS182 Visualizing and Designing Neural Nets

RNNs and Style Transfer

This project had 4 parts including automatic image captioning using first vanilla recurrent neural nets and then LSTM RNNs followed by a section on network activation visualization and finally a cool section on style transfer

Read More

Automatic Image captioning and NLP

This project deals with sequence processing. I use both RNNs and transformers to complete a variety of tasks. Note: private until May 15.

Read More

Natual Adversary Resistant Computer Vision

The final project for this class was an open problem in computer vision. The goal was to improve a CV system trained on tiny imagenet to be more resistant to natural adversarial examples as mentioned here.

Read More