Active-Passive SimStereo – Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods

by   Laurent Jospin, et al.

In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image pair can be identified without ambiguity. However, the projected pattern significantly alters the appearance of the image. If this pattern acts as a form of adversarial noise, it could negatively impact the performance of deep learning-based methods, which are now the de-facto standard for dense stereo vision. In this paper, we propose the Active-Passive SimStereo dataset and a corresponding benchmark to evaluate the performance gap between passive and active stereo images for stereo matching algorithms. Using the proposed benchmark and an additional ablation study, we show that the feature extraction and matching modules of a selection of twenty selected deep learning-based stereo matching methods generalize to active stereo without a problem. However, the disparity refinement modules of three of the twenty architectures (ACVNet, CascadeStereo, and StereoNet) are negatively affected by the active stereo patterns due to their reliance on the appearance of the input images.


page 2

page 4

page 5

page 9

page 10

page 16

page 19

page 20


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...

Active stereo vision three-dimensional reconstruction by RGB dot pattern projection and ray intersection

Active stereo vision is important in reconstructing objects without obvi...

Active Stereo Without Pattern Projector

This paper proposes a novel framework integrating the principles of acti...

Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks

Although convolution neural network based stereo matching architectures ...

Deep Learning Stereo Vision at the edge

We present an overview of the methodology used to build a new stereo vis...

Widening siamese architectures for stereo matching

Computational stereo is one of the classical problems in computer vision...

Stereoscopic Universal Perturbations across Different Architectures and Datasets

We study the effect of adversarial perturbations of images on deep stere...

Please sign up or login with your details

Forgot password? Click here to reset