alexsibir

6dof_face

Codes and data for the TIP 2023 paper: Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image

Face-Renovation

Official repository of the paper "HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment".

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

MoVQGAN

MoVQGAN - model for the image encoding and reconstruction

Hierarchical-Localization

Visual localization made easy with hloc

fold

Unified multidimensional array model that collects nonrectangular shapes, advanced indexing, views and sparsity into a single set of composable abstractions Resources

StyleGANEX

[ICCV 2023] StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

Zero-DCE

Zero-DCE code and model

SORT

Advanced 'Simple Online Real-Time Tracking' implementation in Python

pytorch-tvmisc

Totally Versatile Miscellanea for Pytorch

slambook-en

The English version of 14 lectures on visual SLAM.

FPVT_BMVC22

Code of Pyramid Vision Transformer at BMVC 2022

map-free-reloc

[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

BlendNeRF

Official pytorch implementation of BlendNeRF (ICCV 2023)

rafare

Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs (AAAI 2023 Oral)

BPnP

Back-propagatable PnP

FaceCalibration

Camera Self-Calibration Using Human Faces

Lenta-Hackathon

Code and files for skoltech/lenta hackaton sept.2020

Leaf-diseases-segmentation

Finale project of Deep Learning course

Depth-Enhancement-and-Super-Resolution

Towards Unpaired Depth Enhancement and Super-Resolution in the Wild paper code

InterpretableNeuroDL

hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

ASAPNet

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

unsup3d

(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

unimatch

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

efficient-dl-systems

Efficient Deep Learning Systems course materials (HSE, YSDA)

motion-cosegmentation

Reference code for "Motion-supervised Co-Part Segmentation" paper

Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models