From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
This work addresses the challenge of bridging egocentric and exocentric video domains for researchers in computer vision, though it is incremental as it builds on existing studies of view relationships.
The authors tackled the problem of relating first-person (egocentric) and third-person (exocentric) videos by introducing two datasets (synthetic and real) and exploring synthesis and retrieval tasks, showing that their cGAN can hallucinate egocentric views from exocentric inputs and that synthetic data aids in cross-view retrieval with domain adaptation.
First-person (egocentric) and third person (exocentric) videos are drastically different in nature. The relationship between these two views have been studied in recent years, however, it has yet to be fully explored. In this work, we introduce two datasets (synthetic and natural/real) containing simultaneously recorded egocentric and exocentric videos. We also explore relating the two domains (egocentric and exocentric) in two aspects. First, we synthesize images in the egocentric domain from the exocentric domain using a conditional generative adversarial network (cGAN). We show that with enough training data, our network is capable of hallucinating how the world would look like from an egocentric perspective, given an exocentric video. Second, we address the cross-view retrieval problem across the two views. Given an egocentric query frame (or its momentary optical flow), we retrieve its corresponding exocentric frame (or optical flow) from a gallery set. We show that using synthetic data could be beneficial in retrieving real data. We show that performing domain adaptation from the synthetic domain to the natural/real domain, is helpful in tasks such as retrieval. We believe that the presented datasets and the proposed baselines offer new opportunities for further research in this direction. The code and dataset are publicly available.