Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activitie
s and camera motion, we propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training via coarse 3D localization in a voxel grid and fine-grained offset regression. In this manner, we learn a joint distribution of proposals over multiple views. At inference time, our method operates on single RGB images. We outperform state-of-the-art techniques both on images that visually depart from those of standard benchmarks and on those of the classical Human3.6M dataset.
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exis
ts. Manual annotation is tedious, slow, and error-prone. In this paper, we propose to replace most of the annotations by the use of multiple views, at training time only. Specifically, we train the system to predict the same pose in all views. Such a consistency constraint is necessary but not sufficient to predict accurate poses. We therefore complement it with a supervised loss aiming to predict the correct pose in a small set of labeled images, and with a regularization term that penalizes drift from initial predictions. Furthermore, we propose a method to estimate camera pose jointly with human pose, which lets us utilize multi-view footage where calibration is difficult, e.g., for pan-tilt or moving handheld cameras. We demonstrate the effectiveness of our approach on established benchmarks, as well as on a new Ski dataset with rotating cameras and expert ski motion, for which annotations are truly hard to obtain.
