Corpus ID: 15461319

Symmetry-aware Depth Estimation using Deep Neural Networks

  title={Symmetry-aware Depth Estimation using Deep Neural Networks},
  author={Guilin Liu and C. Yang and Zimo Li and Duygu Ceylan and Qixing Huang},
  journal={arXiv: Computer Vision and Pattern Recognition},
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… Expand
2 Citations
Structure from Motion by Artificial Neural Networks
HybridPose: 6D Object Pose Estimation Under Hybrid Representations


Deep convolutional neural fields for depth estimation from a single image
Designing deep networks for surface normal estimation
Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs
Indoor scene structure analysis for single image depth estimation
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
  • D. Eigen, R. Fergus
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
Discrete-Continuous Depth Estimation from a Single Image
Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples
Estimating image depth using shape collections
Break Ames room illusion