DeepAI AI Chat
Log In Sign Up

Improved Point Transformation Methods For Self-Supervised Depth Prediction

by   Chen Ziwen, et al.

Given stereo or egomotion image pairs, a popular and successful method for unsupervised learning of monocular depth estimation is to measure the quality of image reconstructions resulting from the learned depth predictions. Continued research has improved the overall approach in recent years, yet the common framework still suffers from several important limitations, particularly when dealing with points occluded after transformation to a novel viewpoint. While prior work has addressed this problem heuristically, this paper introduces a z-buffering algorithm that correctly and efficiently handles occluded points. Because our algorithm is implemented with operators typical of machine learning libraries, it can be incorporated into any existing unsupervised depth learning framework with automatic support for differentiation. Additionally, because points having negative depth after transformation often signify erroneously shallow depth predictions, we introduce a loss function to penalize this undesirable behavior explicitly. Experimental results on the KITTI data set show that the z-buffer and negative depth loss both improve the performance of a state of the art depth-prediction network.


page 1

page 2


Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation

Photometric consistency loss is one of the representative objective func...

Geometry meets semantics for semi-supervised monocular depth estimation

Depth estimation from a single image represents a very exciting challeng...

Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

In self-supervised monocular depth estimation, the depth discontinuity a...

Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network

There has been tremendous research progress in estimating the depth of a...

Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss

We present a novel unsupervised learning framework for single view depth...

Quad-networks: unsupervised learning to rank for interest point detection

Several machine learning tasks require to represent the data using only ...