قالب وردپرس درنا توس
Home / Tips and Tricks / Google researchers develop method for capturing & # 39; relightable & # 39; Volumetric Videos «Next Reality

Google researchers develop method for capturing & # 39; relightable & # 39; Volumetric Videos «Next Reality



With increasing demand for realistic volumetric videos for AR experiences (along with the capabilities and services they can capture), researchers at Google have discovered how to improve the format.

The team has a "The Relightables" system consisting of a spherical cage with 330 programmable LED lights and about 100 volumetric video capture cameras.

According to the team, three changes have been made with the Relightables system. First, the system's cameras operate as depth sensors and capture 12.4 megapixel depth maps of the subject. Second, the team created a geometry and machine learning reconstruction pipeline to synthesize video from the acquired data.

Image by AugmentedPerception / YouTube Collects time-synchronized reflection maps of the depth maps that manipulate the subject's lighting in an AR or VR scene instead of keeping the lighting from the original studio. This information is obtained by alternating flashes of two different color gradient patterns, from which the system can deduce the reflection properties of the object during video reconstruction.

After recently releasing the research on Association for Computing Machinery, the team presented its findings at SIGGRAPH Asia 2019.

"While volumetric acquisition systems focused on three-dimensional geometric reconstruction with high-resolution textures have made significant progress much less work has been done to restore the photometric properties required for the re-illumination, "the team wrote in its abstract for the paper.

"In contrast, a large number of relightable acquisition works have been concerned with image-based approaches that photograph the subject under a variety of basic lighting conditions and recombine the images to reveal the motif Its use in the context of o adapted a high-resolution volume acquisition system.This method combines this ability to realistically re-illuminate people for any environment, with the benefits of zero-point volumetric acquisition and new geometric accuracy for dynamic performance. "

image by augmentedperception / YouTube

The volumetric video segment has grown steadily over the last two years: in addition to Microsoft's Mixed Reality Capture Studios, Sony has established its own studio and Verizon Jaunt for entry into the volumetric Acquisition technology adopted.

The use cases for volumetric video in augmented reality experiences are numerous now and in the future. The New York Times has shown how volumetric video can enhance augmented reality content for immersive storytelling. Wall has extended support for the format to its web-based AR platform.

In the meantime, Magic Leap [1] acquired 9459022] Mimesys and its real-time holographic video call technology show how volumetric video capture will change the nature of communications in the near future.

In collaboration with Opera Queensland, Google's Creative Lab has developed yet another use case: virtual opera. The prototype experience, which will be shown for the first time at SIGGRAPH, will include three performers captured via the Relightables system.

With the contribution of Google, the added realism of 3D content from volumetric relightables makes it even harder to distinguish AR from reality.


Source link