Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

TL;DR

This paper introduces a semi-supervised approach for camera viewpoint estimation that leverages unlabeled image pairs to synthesize new images, significantly improving performance in low-label scenarios.

Contribution

It presents a novel geometry-aware conditional generation method for semi-supervised viewpoint estimation, enhancing accuracy with limited labeled data.

Findings

Outperforms state-of-the-art semi-supervised methods

Significantly improves accuracy in low-label regimes

Effective in synthesizing viewpoint changes from unlabeled data

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.