PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning

05/12/2021
by   Yang Xiao, et al.
2

Motivated by the need of estimating the pose (viewpoint) of arbitrary objects in the wild, which is only covered by scarce and small datasets, we consider the challenging problem of class-agnostic 3D object pose estimation, with no 3D shape knowledge. The idea is to leverage features learned on seen classes to estimate the pose for classes that are unseen, yet that share similar geometries and canonical frames with seen classes. For this, we train a direct pose estimator in a class-agnostic way by sharing weights across all object classes, and we introduce a contrastive learning method that has three main ingredients: (i) the use of pre-trained, self-supervised, contrast-based features; (ii) pose-aware data augmentations; (iii) a pose-aware contrastive loss. We experimented on Pascal3D+ and ObjectNet3D, as well as Pix3D in a cross-dataset fashion, with both seen and unseen classes. We report state-of-the-art results, including against methods that use additional shape information, and also when we use detected bounding boxes.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 8

page 14

research
07/27/2021

Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

6D pose estimation of rigid objects from a single RGB image has seen tre...
research
06/12/2019

Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects

Most deep pose estimation methods need to be trained for specific object...
research
06/02/2022

3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation

Image-based object pose estimation sounds amazing because in real applic...
research
06/05/2020

Novel Object Viewpoint Estimation through Reconstruction Alignment

The goal of this paper is to estimate the viewpoint for a novel object. ...
research
04/22/2022

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

In this paper, we present a generalizable model-free 6-DoF object pose e...
research
04/12/2022

Semantic keypoint-based pose estimation from single RGB frames

This paper presents an approach to estimating the continuous 6-DoF pose ...
research
11/22/2022

MagicPony: Learning Articulated 3D Animals in the Wild

We consider the problem of learning a function that can estimate the 3D ...

Please sign up or login with your details

Forgot password? Click here to reset