564 Open source projects that are alternatives of or similar to Demon

Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs.

DeepTAM: Deep Tracking and Mapping https://lmb.informatik.uni-freiburg.de/people/zhouh/deeptam/

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

A deep learning-powered visual navigation engine to enables autonomous navigation of pocket-size quadrotor - running on PULP

A curated list of background subtraction related papers and resources

[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture, Jester, Kinetics and UCF101

A brand logo detection system using tensorflow object detection API.

CVPR 2021 论文和开源项目合集

A light-weight, power efficient, and general purpose convolutional neural network

[CVPR19] FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image

[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps

Pytorch Tutorial, Pytorch with Google Colab, Pytorch Implementations: CNN, RNN, DCGAN, Transfer Learning, Chatbot, Pytorch Sample Codes

A deep neural network for face alignment

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

Deep Learning Models for Face Detection/Recognition/Alignments, implemented in Tensorflow

Implementation of a hierarchical CNN based model to detect Big Five personality traits

BasicOCR是一个致力于解决自然场景文字识别算法研究的项目。该项目由长城数字大数据应用技术研究院佟派AI团队发起和维护。

food image to recipe with deep convolutional neural networks.

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)

Paper reading notes on Deep Learning and Machine Learning

Code for our CVPR 2019 paper: Selective Kernel Networks; See zhihu：https://zhuanlan.zhihu.com/p/59690223

Convolutional Neural Network for Human Activity Recognition in Tensorflow

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

fast BAM/CRAM depth calculation for WGS, exome, or targeted sequencing

Building Convolutional Neural Networks From Scratch using NumPy

RMDL: Random Multimodel Deep Learning for Classification

Codebase for the paper LSTM Fully Convolutional Networks for Time Series Classification

基于视频的目标检测算法研究

Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学

CNN在线识别手写中文。

My personal note about local and global descriptor

A collection of time series prediction methods: rnn, seq2seq, cnn, wavenet, transformer, unet, n-beats, gan, kalman-filter

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

🔥 Reproducibly benchmarking Keras and PyTorch models

Digit recognition with Convolutional Neural Networks in WebGL

CNN+LSTM+CTC based OCR implemented using tensorflow.

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.

仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层；以及图像分类案例及精调网络案例等,持续更新中... ...

Predict Cryptocurrency Price with Deep Learning

CNN-RNN中文文本分类，基于TensorFlow

ARCore Depth Lab is a set of Depth API samples that provides assets using depth for advanced geometry-aware features in AR interaction and rendering. (UIST 2020)

A PyTorch implementation of ESPCN based on CVPR 2016 paper "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network"

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)

Code examples for new APIs of iOS 10.

深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)

Code for "Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views" in CVPR'19

This repository contains the source code of our work on designing efficient CNNs for computer vision

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

(CVPR 2021 Oral) Open World Object Detection

Weakly Supervised Instance Segmentation using Class Peak Response, in CVPR 2018 (Spotlight)

A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN