Pose Estimation Based on 3D Models

06/20/2015

∙

In this paper, we proposed a pose estimation system based on rendered image training set, which predicts the pose of objects in real image, with knowledge of object category and tight bounding box. We developed a patch-based multi-class classification algorithm, and an iterative approach to improve the accuracy. We achieved state-of-the-art performance on pose estimation task.

READ FULL TEXT

Pose Estimation Based on 3D Models

Joint Object Category and 3D Pose Estimation from 2D Images

Car Segmentation and Pose Estimation using 3D Object Models

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation

Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

PrimA6D: Rotational Primitive Reconstruction for Enhanced and Robust 6D Pose Estimation

Pose Estimation Based on 3D Models

Related Research

Joint Object Category and 3D Pose Estimation from 2D Images

Car Segmentation and Pose Estimation using 3D Object Models

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation

Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

PrimA6D: Rotational Primitive Reconstruction for Enhanced and Robust 6D Pose Estimation