VoluMon: Weakly-Supervised Volumetric Monocular Estimation with Ellipsoid Representations

Abstract

Deep learning approaches to estimating 3D object pose and geometry present an attractive alternative to online estimation techniques, which can suffer from significant estimation latency. However, a practical hurdle to training state-of-the-art deep 3D bounding box estimators is collecting a sufficiently large dataset of 3D bounding box labels. In this work, we present a novel framework for weakly supervised volumetric monocular estimation (VoluMon) that requires annotations in the image space only, i.e., associated object bounding box detections and instance segmentation. By approximating object geometry as ellipsoids, we can exploit the dual form of the ellipsoid to optimize with respect to bounding box annotations and the primal form of the ellipsoid to optimize with respect to a segmented pointcloud. For a simulated dataset with access to ground-truth, we show monocular object estimation performance similar to a naive online depth based estimation approach and after online refinement when depth images are available, we also approach the performance of a learned deep 6D pose estimator, which is supervised with projected 3D bounding box keypoints and assumes known model dimensions. Finally, we show promising qualitative results generated from a real-world dataset collected using a stereo pair.