Open-source alternatives to Human Pose Estimation.pytorch

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

AnimatedDrawings is a system for transforming static 2D drawings of humanoid figures into animated characters. It provides a workflow for character rigging, motion mapping, and scene assembly to turn hand-drawn sketches into moving visual sequences. The project utilizes a motion retargeting framework to map movement data from motion capture files onto custom character skeletons regardless of their physical proportions. It employs a rigging tool that uses pose estimation to automatically predict joint locations and create digital skeletons, which can be manually refined to improve animation ac

This project is a computer vision benchmark and image classification dataset used to measure and compare the accuracy of machine learning models. It provides a standardized collection of labeled fashion product images and training data formatted to be compatible with the MNIST dataset structure. The dataset consists of fixed-dimension grayscale images and label-based category mappings, stored in a binary format. It includes pre-split training and testing sets and a static distribution to ensure consistent cross-model benchmarking. The repository supports image classification benchmarking and

Angjoo Kanazawa \ , Shubham Tulsiani \ , Alexei A. Efros, Jitendra Malik

This package contains code for the Deep Multitask Human Sensing (DMHS) method, published in the CVPR 2017 paper Deep Multitask Architecture for Integrated 2D and 3D Human Sensing.

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Official implementation of GANimation. In this work we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describe in a continuous manifold the anatomical facial movements defining a human expression. Our approach permits controlling the magnitude of…

CVPR2018 - pixel embedding & grouping for structured prediction, e.g., instance segmentation

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

Code for PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

"Zero-Shot" Super-Resolution using Deep Internal Learning

Multi-Content GAN for Few-Shot Font Style Transfer at CVPR 2018

Code for our CVPR 2018 paper: "Synthesizing Images of Humans in Unseen Poses"

PyTorch-Pose is a PyTorch implementation of the general pipeline for 2D single human pose estimation. The aim is to provide the interface of the training/inference/evaluation, and the dataloader with various data augmentation options for the most popular human pose databases (e.g., the MPII…

Maxim Berman, Amal Rannen Triki, Matthew B. Blaschko

This sample show how to simply use the ZED with OpenPose, the deep learning framework that detects the skeleton from a single 2D image. The 3D information provided by the ZED is used to place the joints in space. The output is a 3D view of the skeletons.

This is the implementation of Hierarchical Long-term Video Prediction without Supervision, to be published in ICML 2018.

CVPR'18 ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans