Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation

TL;DR

This paper introduces an algorithm that generates parallax motion effects from a single image by combining instance segmentation and depth estimation, enhancing virtual environment experiences.

Contribution

It proposes a novel method using state-of-the-art networks for depth and segmentation to produce high-quality parallax effects from a single image.

Findings

PyD-Net with Mask R-CNN yields good visual quality

Trade-off analysis between efficiency and quality conducted

Experimental results validate the effectiveness of the approach

Abstract

Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user's experience in three-dimensional virtual environments, the motion parallax estimation is a promising technique to achieve this objective. In this paper, we propose an algorithm for generating parallax motion effects from a single image, taking advantage of state-of-the-art instance segmentation and depth estimation approaches. This work also presents a comparison against such algorithms to investigate the trade-off between efficiency and quality of the parallax motion effects, taking into consideration a multi-task learning network capable of estimating instance segmentation and depth estimation at once. Experimental results and visual quality assessment indicate that the PyD-Net network (depth estimation) combined with Mask R-CNN or FBNet networks (instance segmentation) can produce parallax motion effects with good visual quality.