Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation

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 threedimensional 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.

Adaptive Multiplane Image Generation from a Single Internet Picture

“…In this case, the authors generated the training data for depth supervision using Simultaneous Localization and Mapping (SLAM) and SfM algorithms from videos with static content, while the network is optimized for both depth estimation and new view synthesis. Image segmentation has also been explored to simulate motion parallax effect [24]. Other methods propose to learn an LDI relying on intermediate tasks, such as depth and segmentation maps [4,5], or even from pairs of stereo images [36].…”