System and VLSI Implementation of Phase-based View Synthesis

Computer Science Research Notes

2023

In this paper we deal with the problem of real-time virtual view synthesis, which is crucial in practical immersive video systems. The majority of existing real-time view synthesizers described in literature require using dedicated hardware. In the proposed approach, the view synthesis algorithm is implemented on a CPU increasing its usability for users equipped with consumer devices such as personal computers or laptops. The novelty of the proposed algorithm is based on the atomic z-test function, which allows for parallelization of the depth reprojection step, what was not possible in previous works. The proposal was evaluated on a test set containing miscellaneous perspective and omnidirectional sequences, both in terms of quality and computational time. The results were compared to the state-of-the-art view synthesis algorithm – RVS.

Section: Fast Virtual View Synthesismentioning

confidence: 99%

Massively Parallel CPU-based Virtual View Synthesis with Atomic Z-test

Computer Science Research Notes

2023

“…However, most of them require using dedicated FPGA devices (e.g. [Aki15], [Li19]), powerful GPUs (e.g., [Non18], [Zha17]) or even VLSI devices [Hua19]. The necessity of using such devices significantly limits the possibility of developing a cheap, consumer immersive video system.…”

Section: Introductionmentioning

confidence: 99%

Real-time CPU-based View Synthesis for Omnidirectional Video

2022

CSRN

In this paper, the authors describe the real-time CPU-based implementation of the virtual view synthesis algorithm for high-resolution omnidirectional content. The proposed method allows a user of the immersive video virtually navigating within the scene captured by a multiview system comprised of 360-degree or 180-degree cameras. The proposed method does not require using powerful graphic cards as other state-of-the-art real-time synthesis methods. Instead, the emerge of consumer-grade multithreaded CPUs and CPU-based virtual view synthesis, allows further development of cheap, consumer immersive video systems. The proposed method was compared with the state-of-the-art view synthesis algorithm – RVS, both in terms of quality of synthesized views and computational time required for the synthesis, presenting the usefulness of the proposed method.

“…The real-time virtual view synthesis methods are also known, but they usually require dedicated FPGA [Aki15][Li19] [Wan12] or VLSI [Hua19] devices or powerful graphic cards [Non18][Yao16] [Zha17].…”

Section: Introductionmentioning

confidence: 99%

Fast View Synthesis for Immersive Video Systems

Computer Science Research Notes

2020

Immersive video has become a popular research topic recently. However, there are no fast immersive video processing methods, which could be used in practical immersive video systems. In this paper the real-time CPUbased virtual view synthesis method is presented. The proposed method allows a viewer to freely navigate within acquired scene without necessity of using dedicated FPGA devices or powerful graphic cards. Presented view synthesis method can be used in practical immersive video systems, even for ultra-high resolution sequences. In order to present usefulness of proposed method, several implementations and use cases are discussed in the paper.