
Dave Dirnfeld
I am a Ph.D. student at the University of Massachusetts Amherst - Manning College of Information & Computer Sciences with interests in Computer Vision and AI. I work with Prof. Erik Learned-Miller in the Computer Vision Lab, where we investigate camera pose estimation and object segmentation.
Publications

FLIGHT: Fibonacci Lattice-based Inference for Geometric Heading in real-Time
We introduce a novel approach that employs a generalized Hough transform on the unit sphere, $\mathcal{S}^2$, to estiate the camera translation directions. We start by extracting correspondences between two frames and generating a great circle of … Read More

Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video. While camera rotation estimation is a well-studied problem, no previous methods exhibit both high accuracy and acceptable speed in this … Read More
Teaching Assistant
University of Massachusetts AmherstOperating Systems
CS377
Fall 2021 - Current
Columbia UniversityApplied Deep Learning
COMS W4995
Spring 2021
Columbia UniversityFundamentals of Computer Systems
CSEE 3827
Spring 2021, Spring 2019
Columbia UniversityOperating Systems I
COMS W4118
Spring 2020 - Fall 2020
Education
- Sep. 2021 - CurrentPh.D. StudentUniversity of Massachusetts Amherst
- Sep. 2017 - May 2020Bachelor's of Computer ScienceColumbia University
- Sep. 2014 - Dec. 2016Associate's Degree of Computer Information SystemsRockland Community College