DeanHazineh
Researcher in computational imaging, computer vision, optics, and applied machine learning. Read about my work at https://deanhazineh.github.io/
Harvard UniversityCambridge, MA
Pinned Repositories
Deep-Learning-Color-for-Manga
Implements the Pix2Pix TF architecture (cGAN for image translation) in Python 3.5, TF 1.12 to deeplearn colorization for black and white sketches, manga, and anime
DFlat
DFlat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.
DFlat-tensorflow
(Tensorflow Version) D-Flat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.
DiffVis
Coming Soon
Emergent-World-Representations-Othello
A mechanistic interpretability study invvestigating a sequential model trained to play the board game Othello
Hyperspectral_Diffusion
Release of Pre-trained Unconditioned Hyperspectral Patch Diffusion Models that can be used for plug-and-play research
Machine-Learning-Interviews
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
Multi-Image-Synthesis
The code repository for the 2023 ICCP Paper: Polarization Multi-Image Synthesis with Birefringent Metasurfaces
Pix2Pix_Modern
A modern rewrite of the Pix2Pix architecture in pytorch. Basic backbones updated for attention and the usual new practices.
Pytorch-Deep-Learning-Examples
A small collection of .ipynb notebooks that implements basic tests and demos of some repositories published in computer vision journals
DeanHazineh's Repositories
DeanHazineh/DFlat-tensorflow
(Tensorflow Version) D-Flat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.
DeanHazineh/DFlat
DFlat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.
DeanHazineh/Multi-Image-Synthesis
The code repository for the 2023 ICCP Paper: Polarization Multi-Image Synthesis with Birefringent Metasurfaces
DeanHazineh/Deep-Learning-Color-for-Manga
Implements the Pix2Pix TF architecture (cGAN for image translation) in Python 3.5, TF 1.12 to deeplearn colorization for black and white sketches, manga, and anime
DeanHazineh/Emergent-World-Representations-Othello
A mechanistic interpretability study invvestigating a sequential model trained to play the board game Othello
DeanHazineh/Pytorch-Deep-Learning-Examples
A small collection of .ipynb notebooks that implements basic tests and demos of some repositories published in computer vision journals
DeanHazineh/DiffVis
Coming Soon
DeanHazineh/Hyperspectral_Diffusion
Release of Pre-trained Unconditioned Hyperspectral Patch Diffusion Models that can be used for plug-and-play research
DeanHazineh/Machine-Learning-Interviews
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
DeanHazineh/Pix2Pix_Modern
A modern rewrite of the Pix2Pix architecture in pytorch. Basic backbones updated for attention and the usual new practices.