Learning Dense Wide Baseline Stereo Matching for People
This addresses the domain-specific problem of stereo reconstruction for people in wide baseline scenarios, representing an incremental improvement over existing methods.
The paper tackles the problem of limited performance in stereo matching for people across wide baseline views by introducing a framework that learns dense stereo matching from synthetic people data. The method demonstrates improved wide baseline stereo reconstruction on challenging datasets compared to state-of-the-art approaches.
Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A synthetic people stereo patch dataset (S2P2) is introduced to learn wide baseline dense stereo matching for people. The proposed framework not only learns human specific features from synthetic data but also exploits pooling layer and data augmentation to adapt to real data. The network learns from the human specific stereo patches from the proposed dataset for wide-baseline stereo estimation. In addition to patch match learning, a stereo constraint is introduced in the framework to solve wide baseline stereo reconstruction of humans. Quantitative and qualitative performance evaluation against state-of-the-art methods of proposed method demonstrates improved wide baseline stereo reconstruction on challenging datasets. We show that it is possible to learn stereo matching from synthetic people dataset and improve performance on real datasets for stereo reconstruction of people from narrow and wide baseline stereo data.