Abstract
Multi-view autostereoscopic displays provide an immersive, glasses-free 3D viewing experience, but they require correctly filtered content from multiple viewpoints. This, however, cannot be easily obtained with current stereoscopic production pipelines. We provide a practical solution that takes a stereoscopic video as an input and converts it to multi-view and filtered video streams that can be used to drive multi-view autostereoscopic displays. The method combines a phase-based video magnification and an interperspective antialiasing into a single filtering process. The whole algorithm is simple and can be efficiently implemented on current GPUs to yield a near real-time performance. Furthermore, the ability to retarget disparity is naturally supported. Our method is robust and works well for challenging video scenes with defocus blur, motion blur, transparent materials, and specularities. We show that our results are superior when compared to the state-of-the-art depth-based rendering methods. Finally, we showcase the method in the context of a real-time 3D videoconferencing system that requires only two cameras.
Funder
Division of Information and Intelligent Systems
Quanta Computer
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Cited by
30 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Modified 2D-Ghost-Free Stereoscopic Display with Depth-of-Field Effects;ACM Transactions on Multimedia Computing, Communications, and Applications;2023-01-23
2. NeuralPassthrough: Learned Real-Time View Synthesis for VR;Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings;2022-08-07
3. Phase-based side information generation in distributed video coding;Multimedia Tools and Applications;2022-03-15
4. Epipolar plane images based light-field angular super-resolution network;Seventh Asia Pacific Conference on Optics Manufacture and 2021 International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2021);2022-02-15
5. HiddenGazeStereo: Hiding Gaze-Contingent Disparity Remapping for 2D-Compatible Natural 3D Viewing;IEEE Access;2022