SIGNet: Semantic Instance Aided Unsupervised
3D Geometry Perception

Yue Meng	Yongxi Lu	Aman Raj	Samuel Sunarjo	Rui Guo†

Tara Javidi	Gaurav Bansal†	Dinesh Bharadia

University of California, San Diego	Toyota InfoTechnology Center†

CVPR 2019

Abstract

Unsupervised learning for visual perception of 3D geometry is of great interest to autonomous systems. This paper introduces SIGNet, a novel frameworkthat provides robust geometry perception without requiring geometrically informative labels. Specifically, SIGNet integrates semantic information to make unsupervised robust geometric predictions for objects in low lighting and noisy environments. SIGNet is shown to improve upon the state-of-the-art unsupervised learning for geometry perception by 30% (in squared relative error for depth prediction). In addition, SIGNet improves the dynamic object class performance by 39% in depth prediction and 29% in flow prediction.

---

Network

---

Depth Estimation Results on KITTI

---

Robustness & Category-Specific Improvements

---

Paper and Code

		Yue Meng, Yongxi Lu, Aman Raj, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, and Dinesh Bharadia. SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF][Code]

---