Deep Billboards towards Lossless Real2Sim in Virtual Reality
This addresses the limitation of existing VR applications in achieving realistic object representation, potentially enhancing immersive experiences for VR users, though it appears incremental by adapting classic billboards to VR.
The paper tackles the problem of bringing real-world objects into virtual reality (VR) with high realism by developing Deep Billboards, an implicit neural rendering system that enables real-time, high-resolution simulation of diverse objects like rigid, hairy, and dynamic ones, drastically narrowing the real-to-simulation gap.
An aspirational goal for virtual reality (VR) is to bring in a rich diversity of real world objects losslessly. Existing VR applications often convert objects into explicit 3D models with meshes or point clouds, which allow fast interactive rendering but also severely limit its quality and the types of supported objects, fundamentally upper-bounding the "realism" of VR. Inspired by the classic "billboards" technique in gaming, we develop Deep Billboards that model 3D objects implicitly using neural networks, where only 2D image is rendered at a time based on the user's viewing direction. Our system, connecting a commercial VR headset with a server running neural rendering, allows real-time high-resolution simulation of detailed rigid objects, hairy objects, actuated dynamic objects and more in an interactive VR world, drastically narrowing the existing real-to-simulation (real2sim) gap. Additionally, we augment Deep Billboards with physical interaction capability, adapting classic billboards from screen-based games to immersive VR. At our pavilion, the visitors can use our off-the-shelf setup for quickly capturing their favorite objects, and within minutes, experience them in an immersive and interactive VR world with minimal loss of reality. Our project page: https://sites.google.com/view/deepbillboards/