We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).

✭ 194

tensorflow computer-vision neural-network demo real-time pose-estimation webcam

Seismic Deeplearning

Deep Learning for Seismic Imaging and Interpretation

✭ 198

python deep-learning computer-vision neural-networks segmentation microsoft

End To End For Chinese Plate Recognition

基于u-net，cv2以及cnn的中文车牌定位，矫正和端到端识别软件，其中unet和cv2用于车牌定位和矫正，cnn进行车牌识别，unet和cnn都是基于tensorflow的keras实现

✭ 197

python tensorflow computer-vision keras opencv image-segmentation image-recognition

Photo2cartoon

人像卡通化探索项目 (photo-to-cartoon translation project)

✭ 2,845

python deep-learning computer-vision gan avatar-generator cartoon

Semantic Embeddings

Hierarchy-based Image Embeddings for Semantic Image Retrieval

✭ 196

python deep-learning machine-learning computer-vision keras image-retrieval representation-learning

Thor

thor: C++ helper library, for deep learning purpose

✭ 197

computer-vision object-detection deeplearning tracking

Ailearnnotes

Artificial Intelligence Learning Notes.

✭ 195

python deep-learning machine-learning tensorflow computer-vision reinforcement-learning image-processing cnn image-segmentation vgg dropout

Multi Task Learning Pytorch

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

✭ 190

python pascal pytorch computer-vision segmentation

Acurustrack

A multi-object tracking component. Works in the conditions where identification and classical object trackers don't (e.g. shaky/unstable camera footage, occlusions, motion blur, covered faces, etc.). Works on any object despite their nature.

✭ 196

python machine-learning computer-vision artificial-intelligence opencv kalman-filter surveillance

Piccante

The hottest High Dynamic Range (HDR) Library

✭ 195

computer-vision image-processing opengl image-segmentation feature-extraction triangulation

Keras Acgan

Auxiliary Classifier Generative Adversarial Networks in Keras

✭ 196

jupyter-notebook deep-learning tensorflow computer-vision keras gpu generative-adversarial-network

Oicr

Caffe codes for our papers "Multiple Instance Detection Network with Online Instance Classifier Refinement" and "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

✭ 196

python computer-vision object-detection

Horizonnet

Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.

✭ 195

python computer-vision 3d-reconstruction

Tf flame

Tensorflow framework for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 2D or 3D keypoints, and how to generate textured head meshes from Images.

✭ 193

python tensorflow computer-vision 3d computer-graphics face 3d-reconstruction 3d-graphics 3d-models face-alignment

Deep Learning With Python

Deep learning codes and projects using Python

✭ 195

jupyter-notebook deep-learning machine-learning computer-vision keras artificial-intelligence object-detection convolutional-neural-networks neural-networks cnn generative-adversarial-network image-classification rnn recurrent-neural-networks resnet vgg16

Liteflownet2

A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020

✭ 195

python computer-vision cnn deeplearning caffe optical-flow

Miscnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

✭ 194

python deep-learning tensorflow computer-vision framework neural-network convolutional-neural-networks segmentation medical-imaging pip

Cnn Visualization

TensorFlow implementations of visualization of convolutional neural networks, such as Grad-Class Activation Mapping and guided back propagation

✭ 194

python deep-learning computer-vision visualization cnn

Person Detection And Tracking

A tensorflow implementation with SSD model for person detection and Kalman Filtering combined for tracking

✭ 193

python tensorflow computer-vision artificial-intelligence object-detection opencv convolutional-neural-networks tracking

Fashion Recommendation

A clothing retrieval and visual recommendation model for fashion images.

✭ 193

python python3 tensorflow computer-vision numpy pandas resnet

Nlvr

Cornell NLVR and NLVR2 are natural language grounding datasets. Each example shows a visual input and a sentence describing it, and is annotated with the truth-value of the sentence.

✭ 192

html machine-learning computer-vision natural-language-processing corpus

Affnet

Code and weights for local feature affine shape estimation paper "Repeatability Is Not Enough: Learning Discriminative Affine Regions via Discriminability"

✭ 191

python deep-learning pytorch computer-vision convolutional-neural-networks image-retrieval convolutional-networks hessian

Yolov3 Object Detection With Opencv

This project implements a real-time image and video object detection classifier using pretrained yolov3 models.

✭ 191

python deep-learning computer-vision artificial-intelligence object-detection ai yolov3 pretrained-models

Layout Parser

A Python Library for Document Layout Understanding

✭ 191

python deep-learning computer-vision object-detection ocr

Primestereomatch

A heterogeneous and fully parallel stereo matching algorithm for depth estimation, implementing a local adaptive support weight (ADSW) Guided Image Filter (GIF) cost aggregation stage. Developed in both C++ and OpenCL.

✭ 191

c computer-vision algorithm opencv camera opencl

Light Field Video

Light field video applications (e.g. video refocusing, focus tracking, changing aperture and view)

✭ 190

deep-learning computer-vision caffe computer-graphics

Voxel Flow

Video Frame Synthesis using Deep Voxel Flow (ICCV 2017 Oral)

✭ 191

python deep-learning computer-vision generative-model

Metalhead.jl

Computer vision models for Flux