End-to-end Full Projector Compensation

TL;DR

This paper introduces CompenNeSt++, an end-to-end differentiable system for full projector compensation that jointly addresses geometric and photometric distortions, improving accuracy and practicality.

Contribution

It presents the first end-to-end solution combining geometric correction and photometric compensation in a unified framework, with a novel synthetic data pre-training strategy.

Findings

Outperforms prior methods in compensation quality

Reduces training data and time significantly

Provides a setup-independent benchmark for future research

Abstract

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and may suffer from suboptimal solutions. In this paper, we propose the first end-to-end differentiable solution, named CompenNeSt++, to solve the two problems jointly. First, we propose a novel geometric correction subnet, named WarpingNet, which is designed with a cascaded coarse-to-fine structure to learn the sampling grid directly from sampling images. Second, we propose a novel photometric compensation subnet, named CompenNeSt, which is designed with a siamese architecture to capture the photometric interactions between the projection surface and the projected images, and to use such information to compensate the geometrically corrected images. By concatenating WarpingNet with CompenNeSt, CompenNeSt++ accomplishes full projector compensation and is end-to-end trainable. Third, to improve practicability, we propose a novel synthetic data-based pre-training strategy to significantly reduce the number of training images and training time. Moreover, we construct the first setup-independent full compensation benchmark to facilitate future studies. In thorough experiments, our method shows clear advantages over prior art with promising compensation quality and meanwhile being practically convenient.