Dealing With Small Data And Training Blind Spots In The Manhattan World

Leveraging Manhattan assumption we generate metrically rectified novel views from a single image, even for non-box scenarios. Our novel views enable the already trained classifiers to handle training data missing views (blind spots) without additional training. We demonstrate this on end-to-end scene text spotting under perspective. Additionally, utilizing our fronto-parallel views, we discover unsupervised invariant mid-level patches given a few widely separated training examples (small data domain). These invariant patches outperform various baselines on small data image retrieval challenge.