
Autonomous Driving: Boosting Optical Flow with Synthetic Data
- Michael Galarnyk
- April 27, 2023
- computer vision
- optical flow
- synthetic data
Optical flow is defined as the task of estimating per-pixel motion between video frames. Optical flow models take two sequential frames as input and return as output a flow vector that predicts where each pixel in the first frame will be in the second frame. Optical flow is an important task for autonomous driving, but […]
Read More
Generating and Videolizing Agglomerative Processes
- Vincent Granville
- April 17, 2023
This short article explains how to efficiently simulate the evolution of agglomerative processes, and visualize their behavior with data animations. I use a generic, simple model for illustration purposes: atoms, initially consisting of one electron, collide and merge over time, with a pre-specified maximum number of electrons per atom: the maximum limit. Given enough time, […]
Read More
Massively Speed-Up your Learning Algorithm, with Stochastic Thinning
- Vincent Granville
- April 7, 2023
Dramatically Speed-Up your Learning Algorithm, with Stochastic Thinning. Includes use case, Python code, regression and neural network illustrations.
Read More
You must be logged in to post a comment.