BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
Nadine Rüegg, Silvia Zuffi, Konrad Schindler, Michael J. Black
CVPR 2022
Monocular 3D shape and pose regression of 3D dogs from 2D images. Since 3D training data is limited, BARC uses breed information at training time via triplet and classification losses.
Interactive Demo
|
|
Try our model on your own images!
This demo is not running anymore, due to limited GPU access. |
Video
Abstract
Our goal is to recover the 3D shape and pose of dogs from a single image. This is a challenging task because dogs exhibit a wide range of shapes and appearances, and are highly articulated. Recent work has proposed to directly regress the SMAL animal model, with additional limb scale parameters, from images. Our method, called BARC (Breed-Augmented Regression using Classification), goes beyond prior work in several important ways. First, we modify the SMAL shape space to be more appropriate for representing dog shape. But, even with a better shape model, the problem of regressing dog shape from an image is still challenging because we lack paired images with 3D ground truth. To compensate for the lack of paired data, we formulate novel losses that exploit information about dog breeds. In particular, we exploit the fact that dogs of the same breed have similar body shapes. We formulate a novel breed similarity loss consisting of two parts: One term encourages the shape of dogs from the same breed to be more similar than dogs of different breeds. The second one, a breed classification loss, helps to produce recognizable breed-specific shapes. Through ablation studies, we find that our breed losses significantly improve shape accuracy over a baseline without them. We also compare BARC qualitatively to WLDO with a perceptual study and find that our approach produces dogs that are significantly more realistic. This work shows that a-priori information about genetic similarity can help to compensate for the lack of 3D training data. This concept may be applicable to other animal species or groups of species.
Poster
Results
Citation
@inproceedings{barc2022rueegg,
title = {{BARC}: Learning to Regress {3D} Dog Shape from Images by Exploiting Breed Information},
author = {Rueegg, Nadine and Zuffi, Silvia and Schindler, Konrad and Black, Michael J.},
booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
pages={3876--3884},
year = {2022}}