Computer Vision — Week 9
• publicTable of contents
Hey! My name’s Michel Liao. I’m a computer science first-year at Princeton University, hoping to get a PhD in computer vision. Join me in my CV journey!
GitHub: https://github.com/Michel-Liao
Personal Website: https://michelliao.com/
Videos/Lectures
I used this presentation on RAFT by Jonassen Li to inform mine.
This lecture video on residual networks by Professor Bryce Wiedenbeck helped with understanding RAFT’s feature encoder.
This presentation on Optimization Inspired Neural Networks for 3D by Zachary Teed (first author of RAFT) gave a good high-level overview of RAFT as well as RAFT-stereo.
Mini Projects
None. Focused on paper-reading this week.
Course Progress
Finished Improving Deep Neural Networks: Hyperparameter Tuning, Regularization, and Optimization. Notes here.
I also finished Structuring Machine Learning Projects. Notes here.
Now, I’m working on their CNN course.
Paper of the Week
RAFT was sent to me by Erich Liang.
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow - Zachary Teed and Jia Deng
I made a presentation for this paper. I might make a YouTube video about it soon.
Going Forward
I’m going to continue on working on Coursera and reading optical flow papers. If I have time, I’ll implement a NN in PyTorch or write about cross-correlation code from scratch.
