Browse > Computer Vision > Pose Estimation

Pose Estimation

147 papers with code · Computer Vision

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

State-of-the-art leaderboards

Latest papers without code

Learning Loss for Active Learning

CVPR 2019 Donggeun Yoo et al

In this paper, we propose a novel active learning method that is simple but task-agnostic, and works efficiently with the deep networks.

ACTIVE LEARNING IMAGE CLASSIFICATION OBJECT DETECTION POSE ESTIMATION

01 Jun 2019

Parsing R-CNN for Instance-Level Human Analysis

CVPR 2019 Lu Yang et al

Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance.

HUMAN-OBJECT INTERACTION DETECTION HUMAN PART SEGMENTATION MULTI-HUMAN PARSING POSE ESTIMATION

01 Jun 2019

Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering

CVPR 2019 Seungryul Baek et al

Once the model is successfully fitted to input RGB images, its meshes i. e. shapes and articulations, are realistic, and we augment view-points on top of estimated dense hand poses.

3D POSE ESTIMATION HAND POSE ESTIMATION

01 Jun 2019

Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry

CVPR 2019 Muhammed Kocabas et al

Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.

3D HUMAN POSE ESTIMATION

01 Jun 2019

Does Learning Specific Features for Related Parts Help Human Pose Estimation?

CVPR 2019 Wei Tang et al

Can we identify related parts and learn specific features for them to improve pose estimation?

MULTI-TASK LEARNING POSE ESTIMATION

01 Jun 2019

Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification

CVPR 2019 Wenjie Yang et al

The fundamental challenge of small inter-person variation requires Person Re-Identification (Re-ID) models to capture sufficient fine-grained information.

HUMAN PARSING PERSON RE-IDENTIFICATION POSE ESTIMATION

01 Jun 2019

Zero-Shot Task Transfer

CVPR 2019 Arghya Pal et al

In this work, we present a novel meta-learning algorithm that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks).

META-LEARNING POSE ESTIMATION TRANSFER LEARNING ZERO-SHOT LEARNING

01 Jun 2019

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

CVPR 2019 He Wang et al

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image.

6D POSE ESTIMATION

01 Jun 2019

3D Local Features for Direct Pairwise Registration

CVPR 2019 Haowen Deng et al

Our extensive quantitative and qualitative experiments suggests that our approach outperforms the state of the art in challenging real datasets of pairwise registration and that augmenting the keypoints with local pose information leads to better generalization and a dramatic speed-up.

POSE ESTIMATION

01 Jun 2019