In recent years, tremendous amount of progress is being made in the field of Human Pose Estimation from RGB Camera, which is an interdisciplinary field that fuses computer vision, deep/machine learning and anatomy. This repo is for my study notes and will be used as a place for triaging new research papers.
To make it a collaborative project, you may add content through pull requests or open an issue to let me know.
I'll use the following icons and dimensions to differentiate the approaches:
- Time Dimension
- π· Single-Shot
- π₯ Video/Real-Time
- Number of People
- 1οΈβ£ Single-Person
- π’ Multi-Person
- Spatial Dimensions
π₯π’ Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (2017) [Project page][Paper]
π·1οΈβ£ Stacked Hourglass Networks for Human Pose Estimation (2016) [Paper]
π·1οΈβ£ Convolutional Pose Machines (2016) [Paper]
π·1οΈβ£ Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation (2017) [Paper]
π·1οΈβ£ Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation (2017) [Project page] [Paper]
π·1οΈβ£ A simple yet effective baseline for 3d human pose estimation (2017) [Project page][Paper]
π₯1οΈβ£ VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera (2017) [Project page][Paper]
π·π’ Single-Shot Multi-Person 3D Body Pose Estimation From Monocular RGB Input (2018) [Paper]
π·1οΈβ£ Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision (2017) [Project page][Paper]
π·π’ DensePose: Dense Human Pose Estimation In The Wild (2018) [Project page][Paper]
π₯1οΈβ£ End-to-end Recovery of Human Shape and Pose (2017) [Project page][Paper]
π₯π’ LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images (2018) [Project page][Paper]
π₯1οΈβ£ Spatio-temporal Matching for Human Pose Estimation (2014) [Project page][Paper]
π₯1οΈβ£ Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2016) [Paper]
π·1οΈβ£ Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2017) [Paper]
π·1οΈβ£ Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016) [Paper]
π·1οΈβ£ MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild (2016) [Paper]
π·1οΈβ£ Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image (2017) [Paper]
π₯1οΈβ£ MonoPerfCap: Human Performance Capture from Monocular Video (2018) [Project page] [Paper]
π·1οΈβ£ Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations (2018) [Project page] [Paper]
π·1οΈβ£ 3D Human Pose Estimation in the Wild by Adversarial Learning (2018) [Paper]
π·π’ Deep Human Pose Estimation Using Cascade of Multiple Neural Networks (2018) [Paper]
π₯1οΈβ£ Deep 3D Human Pose Estimation Under Partial Body Presence (2018) [Paper]
π₯1οΈβ£ 3D Ego-Pose Estimation via Imitation Learning (2018) [Paper]
π·1οΈβ£ Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation (2018) [Paper]