Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks

by   Can Pu, et al.

Fusing disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships between neighboring pixels limit the accuracy and robustness of the existing methods and there is no common method for depth fusion of different kind of data. In this paper, we introduce a method to incorporate supplementary information (intensity, gradient constraints etc.) into a Generative Adversarial Network to better refine each input disparity value. By adopting a multi-scale strategy, the disparity relationship in the fused disparity map is a better estimate of the real distribution. The approach includes a more robust object function to avoid blurry edges, impaints invalid disparity values and requires much fewer ground data to train. The algorithm can be generalized to different kinds of depth fusion. The experiments were conducted through simulation and real data, exploring different fusion opportunities: stereo-monocular fusion from coarse input, stereo-stereo fusion from moderately accurate input, fusion from accurate binocular input and Time of Flight sensor. The experiments show the superiority of the proposed algorithm compared with the most recent algorithms on the public Scene Flow and SYNTH3 datasets. The code is available from


page 5

page 11

page 12

page 13

page 14


UDFNet: Unsupervised Disparity Fusion with Adversarial Networks

Existing disparity fusion methods based on deep learning achieve state-o...

MSDC-Net: Multi-Scale Dense and Contextual Networks for Automated Disparity Map for Stereo Matching

Disparity prediction from stereo images is essential to computer vision ...

Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision

A major focus of recent developments in stereo vision has been on how to...

Environment reconstruction on depth images using Generative Adversarial Networks

Robust perception systems are essential for autonomous vehicle safety. T...

DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels

In the context of scene understanding, a variety of methods exists to es...

Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network

Stereo superpixel segmentation aims at grouping the discretizing pixels ...

SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation

Recently, over-height vehicle strike frequently occurs, causing great ec...

Please sign up or login with your details

Forgot password? Click here to reset