Can I read Data Augmentation for Object Detection via Differentiable Neural Rendering on EtoBox?

Data Augmentation for Object Detection via Differentiable Neural Rendering by Ning, Guanghan; Chen, Guang; Tan, Chaowei; Luo, Si; Bo, Liefeng; Huang, Heng is a scholarly article available to read on EtoBox.

What is Data Augmentation for Object Detection via Differentiable Neural Rendering about?

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that interpolate labeled data from unlabeled data, and self-supervised learning approaches that exploit signals within unlabeled data via pretext tasks. To seamlessly integrate and enhance existing supervised object detection methods, in this work, we focus on addressing the data scarcity problem from a fundamental viewpoint without changing the supervised learning paradigm. We propose a new offline data augmentation method for object detection, which semantically interpolates the training data with novel views. Specifically, our new system generates controllable views of training images based on differentiable neural rendering, together with corresponding bounding box annotations which involve no human intervention. Firstly, we extract and project pixel-aligned image features into point clouds while estimating depth maps. We then re-project them with a target camera pose and render a novel-view 2d image. Objects in the form of keypoints are marked in point

Author

Ning, Guanghan; Chen, Guang; Tan, Chaowei; Luo, Si; Bo, Liefeng; Huang, Heng

Published

2021

Language

EN