Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

Abstract

There is a growing interest in developing computer vision methods that can learn from limited supervision. In this paper, we consider the problem of learning to predict camera viewpoints, where obtaining ground-truth annotations are expensive and require special equipment, from a limited number of labeled images. We propose a semi-supervised viewpoint estimation method that can learn to infer viewpoint information from unlabeled image pairs, where two images differ by a viewpoint change. In particular our method learns to synthesize the second image by combining the appearance from the first one and viewpoint from the second one. We demonstrate that our method significantly improves the supervised techniques, especially in the low-label regime and outperforms the state-of-the-art semi-supervised methods.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• mixup: Beyond Empirical Risk Minimization
• ShapeNet: An Information-Rich 3D Model Repository
• Unsupervised Data Augmentation for Consistency Training
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Deep Convolutional Inverse Graphics Network
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
• Unsupervised learning of object frames by dense equivariant image labelling