johannakarras

DreamPose

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

Deep-Neural-Networks-for-Black-Hole-Imaging

deepsort_object_tracking

consistent_depth

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

cosense

Learning a probabilistic strategy for computational imaging sensor selection (cosense)

CSE517-Final-Project

A reproducibility experiment of the paper "Does Vision-and-Language Pretraining Improve Lexical Grounding?" by Tian Yun, Chen Sun, and Ellie Pavlick, published at EMNLP 2021.

DeepV2D

EE148-Detecting-Red-Traffic-Lights

Caltech CNS/EE/CS 148 HW 1

EE148-Detecting-Red-Traffic-Lights-pt2

EE/CNS/CS HW2

EE148-MNIST-Classification-CNN

Classification of MNIST handwritten digits using convolutional neural networks.

johannakarras.github.io

minimal

Minimal is a Jekyll theme for GitHub Pages

pix2pixHD

Synthesizing and manipulating 2048x1024 images with conditional GANs

pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch

reproducibility-vlm-lexical-grounding

PyTorch code for the Findings of EMNLP 2021 paper "Does Vision-and-Language Pretraining Improve Lexical Grounding?"