Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
Monocular estimation of 3d human pose has attracted in- creased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent methods generalize outside the specific datasets they are trained on. In this work we carry out a systematic study of the diversity and biases present in specific datasets and its e↵ect on cross-dataset generalization across a compendium of 5 pose datasets. We specifically focus on systematic di↵erences in the distri- bution of camera viewpoints relative to a body-centered coordinate frame. Based on this observation, we propose an auxiliary task of predicting the camera viewpoint in addition to pose. We find that models trained to jointly predict viewpoint and pose systematically show significantly improved cross-dataset generalization.Free, publicly-accessible full text available October 11, 2022
Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predic- tors fail to make reliable depth predictions for testing exam- ples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we in- troduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consis- tent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly ap- plying the two methods improves depth prediction on im- ages captured under uncommon and even never-before-seen camera poses. We show that our methods improve perfor- mance when applied to a range of different predictor ar- chitectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization per- formance of a synthetically trained depth predictor when evaluated on real images.