@phdthesis{JanaiThesis2020,
  title = {Addressing the Data Scarcity of Learning-based Optical Flow Approaches},
  abstract = {Learning to solve optical flow in an end-to-end fashion from examples is attractive as deep neural networks allow for learning more complex hierarchical flow representations directly from annotated data. However, training such models requires large datasets, and obtaining ground truth for real images is challenging. Due to the difficulty of capturing dense ground truth, existing optical flow datasets are limited in size and diversity. Therefore, we present two strategies to address this data scarcity problem: First, we propose an approach to create new real-world datasets by exploiting temporal constraints using a high-speed video camera. We tackle this problem by tracking pixels through densely sampled space-time volumes recorded with a high-speed video camera. Our model exploits the linearity of small motions and reasons about occlusions from multiple frames. Using our technique, we are able to establish accurate reference flow fields outside the laboratory in natural environments. Besides, we show how our predictions can be used to augment the input images with realistic motion blur. We demonstrate the quality of the produced flow fields on synthetic and real-world datasets. Finally, we collect a novel challenging optical flow dataset by applying our technique on data from a high-speed camera and analyze the performance of state of the art in optical flow under various levels of motion blur. Second, we investigate how to learn sophisticated models from unlabeled data. Unsupervised learning is a promising direction, yet the performance of current unsupervised methods is still limited. In particular, the lack of proper occlusion handling in commonly used data terms constitutes a major source of error. While most optical flow methods process pairs of consecutive frames, more advanced occlusion reasoning can be realized when considering multiple frames. We propose a framework for unsupervised learning of optical flow and occlusions over multiple frames. More specifically, we exploit the minimal configuration of three frames to strengthen the photometric loss and explicitly reason about occlusions. We demonstrate that our multi-frame, occlusion-sensitive formulation outperforms previous unsupervised methods and even produces results on par with some fully supervised methods. Both directions are essential for future advances in optical flow. While new datasets allow measuring the advancements and comparing novel approaches, unsupervised learning permits the usage of new data sources to train better models.},
  degree_type = {PhD},
  institution = {University of Tübingen},
  month = jul,
  year = {2020},
  slug = {janaithesis2020},
  author = {Janai, Joel},
  month_numeric = {7}
}