-
[pdf]
[bibtex]@InProceedings{Lin_2023_WACV, author = {Lin, Kelly X. and Cho, Irene and Walimbe, Amey and Zamora, Bryan A. and Rich, Alex and Zhang, Sirius Z. and H\"ollerer, Tobias}, title = {Benefits of Synthetically Pre-Trained Depth-Prediction Networks for Indoor/Outdoor Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2023}, pages = {360-369} }
Benefits of Synthetically Pre-Trained Depth-Prediction Networks for Indoor/Outdoor Image Classification
Abstract
Ground truth depth information is necessary for many computer vision tasks. Collecting this information is challenging, especially for outdoor scenes. In this work, we propose utilizing single-view depth prediction neural networks pre-trained on synthetic scenes to generate relative depth, which we call pseudo-depth. This approach is a less expensive option as the pre-trained neural network obtains accurate depth information from synthetic scenes, which does not require any expensive sensor equipment and takes less time. We measure the usefulness of pseudo-depth from pre-trained neural networks by training indoor/outdoor binary classifiers with and without it. We also compare the difference in accuracy between using pseudo-depth and ground truth depth. We experimentally show that adding pseudo depth to training achieves a 4.4% performance boost over the non-depth baseline model on DIODE, a large standard test dataset, retaining 63.8% of the performance boost achieved from training a classifier on RGB and ground truth depth. It also boosts performance by 1.3% on another dataset, SUN397, for which ground truth depth is not available. Our result shows that it is possible to take information obtained from a model pre-trained on synthetic scenes and successfully apply it beyond the synthetic domain to real-world data.
Related Material