Symmetry-aware Depth Estimation using Deep Neural Networks
This addresses the problem of recovering depth information from abundant 2D product images for applications requiring 3D reconstruction, though it is incremental as it builds on existing convolutional neural network approaches.
The paper tackles single-view depth estimation from 2D product images by incorporating symmetry information, which is common in man-made objects, resulting in a method that outperforms state-of-the-art techniques.
Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications. Recent works have addressed the single-view depth estimation problem by utilizing convolutional neural networks. In this paper, we show that exploring symmetry information, which is ubiquitous in man made objects, can significantly boost the quality of such depth predictions. Specifically, we propose a new convolutional neural network architecture to first estimate dense symmetric correspondences in a product image and then propose an optimization which utilizes this information explicitly to significantly improve the quality of single-view depth estimations. We have evaluated our approach extensively, and experimental results show that this approach outperforms state-of-the-art depth estimation techniques.