Browse SoTA > Computer Vision > Pose Estimation

# Pose Estimation Edit

434 papers with code · Computer Vision

Pose Estimation is a general problem in Computer Vision where we detect the position and orientation of an object.

# Greatest papers with code

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

66,872

# Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object.

65,338

# Learning from Simulated and Unsupervised Images through Adversarial Training

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.

61,324

# DensePose: Dense Human Pose Estimation In The Wild

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation.

23,788

# Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.

Ranked #7 on Keypoint Detection on COCO (Validation AP metric)

23,788

# OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

18 Dec 2018CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

18,975

# Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

We present an approach to efficiently detect the 2D pose of multiple people in an image.

18,975

# Convolutional Pose Machines

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models.

18,975

# KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

We address two problems: first, we establish an easy method for capturing and labeling 3D keypoints on desktop objects with an RGB camera; and second, we develop a deep neural network, called $KeyPose$, that learns to accurately predict object poses using 3D keypoints, from stereo input, and works even for transparent objects.

13,277

# Deep High-Resolution Representation Learning for Visual Recognition

20 Aug 2019open-mmlab/mmdetection

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.

12,211