yileichen123

DistilPose

Implementation for: DistilPose: Tokenized Pose Regression with Heatmap Distillation (CVPR2023)

Awesome-Incremental-Learning

Awesome Incremental Learning

IHL

TimeSformer

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

PoseTrans

code of "PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation" (ECCV 2022)

MonocularTotalCapture

Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"

MonocularTotalCapture

Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"

contact-human-dynamics

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

UniPose

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.

PCT

This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)

golfdb

GolfDB is a video database for Golf Swing Sequencing, which involves detecting 8 golf swing events in trimmed golf swing videos. This repo demos the baseline model, SwingNet.

iclr2017mcnet

Tensorflow implementation of the ICLR 2017 paper: Decomposing Motion and Content for Natural Video Sequence Prediction

phd

Code for ICCV 2019 Paper: "Predicting 3D Human Dynamics from Video"

human_dynamics

Project for paper "Learning 3D Human Dynamics from Video"

hmr

Project page for End-to-end Recovery of Human Shape and Pose

LDNet

PoseTriplet

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

EvoSkeleton

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"

Split-and-Recombine-Net

Code for "SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach" ECCV'20

Skeletal-GNN

Code for "Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation" ICCV'21

acton

Code for paper: Towards Tokenized Human Dynamics Representation

AdaptPose

[CVPR 2022] AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

PoseAug

[CVPR 2021] PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation, (Oral, Best Paper Award Finalist)

RepNet

This is the original RepNet implementation

Key-Frame-Proposal-Network-for-Efficient-Pose-Estimation-in-Videos

This is the official implementation for ECCV20 paper: Key Frame Proposal Network for Efficient Pose Estimation in Videos

MixSTE

Official implementation of CVPR 2022 paper(MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video)

3dpose_gan_pytorch

Pytorch implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

3dpose_gan

The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

c3dpo_nrsfm

C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.