MBW: Multiview-bootstrapping in the Wild

1Carnegie Mellon University, 2Apple, 3The University of Adelaide

Conference on Neural Information Processing Systems (NeurIPS), 2022

MBW obtains high-fidelity 2D and 3D landmark labels for deformable object categories from videos with only two or three uncalibrated, handheld cameras moving in the wild.

Abstract

Labeling articulated objects in unconstrained settings have a wide variety of applications including entertainment, neuroscience, psychology, ethology, and many fields of medicine. Large offline labeled datasets do not exist for all but the most common articulated object categories (e.g., humans).

Hand labeling these landmarks within a video sequence is a laborious task. Learned landmark detectors can help, but can be error-prone when trained from only a few examples. Multi-camera systems that train fine-grained detectors have shown significant promise in detecting such errors, allowing for self-supervised solutions that only need a small percentage of the video sequence to be hand-labeled. The approach, however, is based on calibrated cameras and rigid geometry, making it expensive, difficult to manage, and impractical in real-world scenarios.

In this paper, we address these bottlenecks by combining a non-rigid 3D neural prior with deep flow to obtain high-fidelity landmark estimates from videos with only two or three uncalibrated, handheld cameras. With just a few annotations (representing 1-2% of the frames), we are able to produce 2D results comparable to state-of-the-art fully supervised methods, along with 3D reconstructions that are impossible with other existing approaches.

Our Multi-view Bootstrapping in the Wild (MBW) approach demonstrates impressive results on standard human datasets, as well as tigers, cheetahs, fish, colobus monkeys, chimpanzees, and flamingos from videos captured casually in a zoo. We release the codebase for MBW as well as this challenging zoo dataset consisting image frames of tail-end distribution categories with their corresponding 2D, 3D labels generated from minimal human intervention.

Video (short)

Video (detailed)

BibTeX

@inproceedings{dabhi2022mbw,
  author       = {Dabhi, Mosam and Wang, Chaoyang and Clifford, Tim and Jeni, Laszlo and Fasel, Ian and Lucey, Simon},
  title        = {MBW: Multi-view Bootstrapping in the Wild},
  organization = {NeurIPS},
  booktitle    = {Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year         = {2022}
}