Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation
This work addresses improving user experience in virtual and augmented reality applications, but it is incremental as it builds on existing segmentation and depth estimation methods.
The paper tackled generating parallax motion effects from a single image to enhance 3D virtual environments, achieving good visual quality by combining PyD-Net for depth estimation with Mask R-CNN or FBNet for instance segmentation.
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.