3D Pose Estimation for Fine-Grained Object Categories
Abstract
Existing object pose estimation datasets are related to generic object types and there is so far no dataset for fine-grained object categories. In this work, we introduce a new large dataset to benchmark pose estimation for fine-grained objects, thanks to the availability of both 2D and 3D fine-grained data recently. Specifically, we augment two popular fine-grained recognition datasets (StanfordCars and CompCars) by finding a fine-grained 3D CAD model for each sub-category and manually annotating each object in images with 3D pose. We show that, with enough training data, a full perspective model with continuous parameters can be estimated using 2D appearance information alone. We achieve this via a framework based on Faster/Mask R-CNN. This goes beyond previous works on category-level pose estimation, which only estimate discrete/continuous viewpoint angles or recover rotation matrices often with the help of key points. Furthermore, with fine-grained 3D models available, we incorporate a dense 3D representation named as location field into the CNN-based pose estimation framework to further improve the performance. The new dataset is available at www.umiacs.umd.edu/~wym/3dpose.html
Cite
@article{arxiv.1806.04314,
title = {3D Pose Estimation for Fine-Grained Object Categories},
author = {Yaming Wang and Xiao Tan and Yi Yang and Xiao Liu and Errui Ding and Feng Zhou and Larry S. Davis},
journal= {arXiv preprint arXiv:1806.04314},
year = {2018}
}
Comments
4th International Workshop on Recovering 6D Object Pose (ECCVW 2018). arXiv admin note: text overlap with arXiv:1810.09263