PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
arXiv:2105.05643
Abstract
Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without CAD model 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. 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+, ObjectNet3D and Pix3D in a cross-dataset fashion, with both seen and unseen classes. We report state-of-the-art results, including against methods that additionally use CAD models as input.
arXiv comment3DV 2021 (oral). See project webpage http://imagine.enpc.fr/~xiaoy/PoseContrast/
References in corpus (8)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Improved Baselines with Momentum Contrastive Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Learning deep representations by mutual information estimation and maximization
- 3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings
- Self-supervised 6D Object Pose Estimation for Robot Manipulation
- Few-Shot Viewpoint Estimation
- 3D Pose Estimation for Fine-Grained Object Categories