kregmi
Ph.D, UCF Center for Research in Computer Vision (CRCV) specialized in computer vision, deep learning.
University of Central FloridaOrlando, FL
Pinned Repositories
CapsPix2Pix
Code for Image Synthesis with a Convolutional Capsule Generative Adversarial Network
cross-view-image-matching
[ICCV 2019] Bridging the Domain Gap for Ground-to-Aerial Image Matching
cross-view-image-synthesis
[CVPR 2018] Cross-View Image Synthesis using Conditional GANs, [CVIU 2019] Cross-view image synthesis using geometry-guided conditional GANs
fastdvdnet
FastDVDnet: A Very Fast Deep Video Denoising algorithm
frame-predict-VAE-LSTM
Predicting image frames using autoencoder and LSTM
Hand-Segmentation-in-the-Wild
kregmi.github.io
mv3d
Multi-view 3D Models from Single Images with a Convolutional Network
triplet-reid-pytorch
A pytorch implementation of the "In Defense of the Triplet Loss for Person Re-Identification" paper (https://arxiv.org/abs/1703.07737). It also contains a implementation of the MGN network from the paper "Learning Discriminative Features with Multiple Granularities for Person Re-Identification". Reaches 83.17% mAP with MGN.
VTE
video trajectory estimation
kregmi's Repositories
kregmi/cross-view-image-synthesis
[CVPR 2018] Cross-View Image Synthesis using Conditional GANs, [CVIU 2019] Cross-view image synthesis using geometry-guided conditional GANs
kregmi/cross-view-image-matching
[ICCV 2019] Bridging the Domain Gap for Ground-to-Aerial Image Matching
kregmi/VTE
video trajectory estimation
kregmi/CapsPix2Pix
Code for Image Synthesis with a Convolutional Capsule Generative Adversarial Network
kregmi/fastdvdnet
FastDVDnet: A Very Fast Deep Video Denoising algorithm
kregmi/frame-predict-VAE-LSTM
Predicting image frames using autoencoder and LSTM
kregmi/Hand-Segmentation-in-the-Wild
kregmi/kregmi.github.io
kregmi/mv3d
Multi-view 3D Models from Single Images with a Convolutional Network
kregmi/triplet-reid-pytorch
A pytorch implementation of the "In Defense of the Triplet Loss for Person Re-Identification" paper (https://arxiv.org/abs/1703.07737). It also contains a implementation of the MGN network from the paper "Learning Discriminative Features with Multiple Granularities for Person Re-Identification". Reaches 83.17% mAP with MGN.