Browse SoTA > Computer Vision > Pose Estimation

Pose Estimation

349 papers with code ยท Computer Vision

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

( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )

Benchmarks

Latest papers without code

Key Frame Proposal Network for Efficient Pose Estimation in Videos

30 Jul 2020

Human pose estimation in video relies on local information by either estimating each frame independently or tracking poses across frames.

POSE ESTIMATION

Event-based Stereo Visual Odometry

30 Jul 2020

We present a solution to the problem of visual odometry from the data acquired by a stereo event-based camera rig.

3D RECONSTRUCTION POSE ESTIMATION VISUAL ODOMETRY

SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data

30 Jul 2020

Additionally, we present our model's 3D surface normal predictions on the MSCOCO dataset that lacks any real 3D surface normal labels.

DOMAIN GENERALIZATION MULTI-TASK LEARNING POSE ESTIMATION

On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures

28 Jul 2020

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks.

ACTION RECOGNITION IMAGE COMPRESSION MONOCULAR DEPTH ESTIMATION OBJECT DETECTION POSE ESTIMATION QUANTIZATION SEMANTIC SEGMENTATION VIDEO COMPRESSION

Multi-camera Torso Pose Estimation using Graph Neural Networks

28 Jul 2020

The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125 mm for the location and 10 degrees for the orientation using low-resolution RGB images.

POSE ESTIMATION

Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions

28 Jul 2020

Autonomous racing provides the opportunity to test safety-critical perception pipelines at their limit.

OBJECT DETECTION POSE ESTIMATION

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

27 Jul 2020

3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars.

3D HUMAN POSE ESTIMATION 3D SHAPE RECONSTRUCTION ACTIVITY RECOGNITION CONTRASTIVE LEARNING SELF-SUPERVISED LEARNING SUPER-RESOLUTION

Robust Image Retrieval-based Visual Localization using Kapture

27 Jul 2020

In this paper, we present a versatile method for visual localization.

IMAGE RETRIEVAL POSE ESTIMATION VISUAL LOCALIZATION

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

26 Jul 2020

GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass.

3D SHAPE REPRESENTATION 6D POSE ESTIMATION

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

23 Jul 2020

The modules of HGG can be trained end-to-end with the keypoint detection network and is able to supervise the grouping process in a hierarchical manner.

GRAPH CLUSTERING HUMAN DETECTION KEYPOINT DETECTION MULTI-PERSON POSE ESTIMATION