Minimal implementation of Denoised Smoothing in TensorFlow
Minimal implementation of Denoised Smoothing: A Provable Defense for Pretrained Classifiers in TensorFlow.
Autonomous Driving project for Euro Truck Simulator 2
Autonomous Driving project for Euro Truck Simulator 2
Single Image Pretraining of Visual Representations With Python
Code for generating a single image pretraining dataset
Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
Scenic: A Jax Library for Computer Vision and Beyond
Scenic is a codebase with a focus on research around attention-based models for computer vision.
A New Lightweight Object Detection System for Edge Computing
A New Lightweight Object Detection System for Edge Computing
Internal Video Inpainting by Implicit Long-range Propagation in python
Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation
Video Contrastive Learning with Global Context (VCLR)
Video Contrastive Learning with Global Context (VCLR)
Seeks to remove text from an image in a convincing way
This is a Computer Vision project that seeks to successfully remove text from an image by covering the text areas in a convincing way.
A collection of Jupyter notebooks for learning and experimenting with OpenVINO
A collection of ready-to-run Jupyter* notebooks for learning and experimenting with the OpenVINO™ Toolkit. T
Create a classifier that interprets the Brazilian Sign Language in python
This project demonstrates the use of neural networks and computer vision to create a classifier that interprets the Brazilian Sign Language.
A simple and effective query based instance segmentation method driven
A simple and effective query based instance segmentation method driven
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
This project is the implement of RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation.
A DeepStack custom model for detecting common objects in dark/night images and videos
A DeepStack custom model for detecting common objects in dark/night images and videos
MLP-Mixer: An all-MLP Architecture for Vision
This repo contains PyTorch implementation of MLP-Mixer: An all-MLP Architecture for Vision.
CAT-Net: Learning Canonical Appearance Transformations
Code to accompany our paper "How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change".
Image Deblurring using Generative Adversarial Networks
Pytorch implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks.
A neuroanatomy-based augmented reality experience with python
A neuroanatomy-based augmented reality experience powered by computer vision that features 3D visuals of the Atlas Brain Map slices.
The AugNet Python module contains functions for the fast computation of image similarity
AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation
Improving Adversarial Transferability of Vision Transformers In Python
Official repository for "On Improving Adversarial Transferability of Vision Transformers" (2021)
Pay Less Attention in Vision Transformers With Python
Official PyTorch implementation of Less is More: Pay Less Attention in Vision Transformers.
Full-Resolution Correspondence Learning for Image Translation
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
Cross Attention in Vision Transformer with python
This is official implement of "CAT: Cross Attention in Vision Transformer".
Tensorflow implementation of MIRNet for Low-light image enhancement
Tensorflow implementation of the MIRNet architecture as proposed by Learning Enriched Features for Real Image Restoration and Enhancement.
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Delving into Deep Imbalanced Regression in python
This repository contains the implementation code for paper:Delving into Deep Imbalanced Regression
Single Image Depth Prediction with Wavelet Decomposition in python
[CVPR 2021] Monocular depth estimation using wavelets for efficiency
Unofficial PyTorch implementation of MaskFlownet
Pytorch implementation of MaskFlownet
Intriguing Properties of Vision Transformers in python
Official repository for "Intriguing Properties of Vision Transformers" (2021)
Mean Shift for Self-Supervised Learning in python
Official code for "Mean Shift for Self-Supervised Learning"
A simple way to achieve SOTA in vision classification with only a single transformer encoder
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
A region-based Siamese Multi-Object Tracking network
SiamMOT is a region-based Siamese Multi-Object Tracking network that detects and associates object instances simultaneously.
End-to-End Pre-training for Vision-Language Representation Learning
Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning [CVPR'21, Oral]
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks (SDPoint)
Build a model/agent that move objects in a room in python
The goal of this challenge is to build a model/agent that move objects in a room to restore them to a given initial configuration.
Deep Two-View Structure-from-Motion Revisited
This repository provides the code for our CVPR 2021 paper Deep Two-View Structure-from-Motion Revisited.
Pytorch implementation of the DeepDream computer vision algorithm
Pytorch implementation of the DeepDream computer vision algorithm
An image processing library in JAX, for JAX
PIX is an image processing library in JAX, for JAX.
Numerical Methods with Python, Numpy and Matplotlib
Collections of numerical techniques with Python and standard computational packages
Convolutional Hough Matching Networks in python
Official PyTorch Implementation of Convolutional Hough Matching Networks, CVPR 2021 (oral)
Python Interactive Graphical System made during Computer Graphics classes
Python Interactive Graphical System made during Computer Graphics classes (INE5420-2021.1)
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
An amazing blend of Computer vision and Video Game in python
This project is an amazing blend of Computer vision and Video Game.
A library for building high-performance custom pose estimation applications
HyperPose is a library for building high-performance custom pose estimation applications.
A technology that adds computer-generated virtual content to real-world views through devices
The development of areas such as computer vision, image processing, and computer graphics, allow the introduction of technologies such as Augmented Reality.
Python based SDK for multi human pose estimation through RGB webcam
PoseCamera is python based SDK for multi human pose estimation through RGB webcam.
Global Filter Networks for Image Classification
Global Filter Networks is a transformer-style architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity.
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Unified tracking framework with a single appearance model
Paper: Do different tracking tasks require different appearance model?