High-precision virtual environments are increasingly important for various education, simulation, training, performance, and entertainment applications. We present HoloCamera, an innovative volumetric capture instrument to rapidly acquire, process, and create cinematic-quality virtual avatars and scenarios. The HoloCamera consists of a custom-designed free-standing structure with 300 high-resolution RGB cameras mounted with uniform spacing spanning the four sides and the ceiling of a room-sized studio. The light field acquired from these cameras is streamed through a distributed array of GPUs that interleave the processing and transmission of 4K resolution images. The distributed compute infrastructure that powers these RGB cameras consists of 50 Jetson AGX Xavier boards, with each processing unit dedicated to driving and processing imagery from six cameras. A high-speed Gigabit Ethernet network fabric seamlessly interconnects all computing boards. In this systems paper, we provide an in-depth description of the steps involved and lessons learned in constructing such a cutting-edge volumetric capture facility that can be generalized to other such facilities. We delve into the techniques employed to achieve precise frame synchronization and spatial calibration of cameras, careful determination of angled camera mounts, image processing from the camera sensors, and the need for a resilient and robust network infrastructure. To advance the field of volumetric capture, we are releasing a high-fidelity static light-field dataset, which will serve as a benchmark for further research and applications of cinematic-quality volumetric light fields.

We present VIINTER, a method for view interpolation by interpolating the implicit neural representation (INR) of the captured images. We leverage the learned code vector associated with each image and interpolate between these codes to achieve viewpoint transitions. We propose several techniques that significantly enhance the interpolation quality. VIINTER signifies a new way to achieve view interpolation without constructing 3D structure, estimating camera poses, or computing pixel correspondence. We validate the effectiveness of VIINTER on several multi-view scenes with different types of camera layout and scene composition. As the development of INR of images (as opposed to surface or volume) has centered around tasks like image fitting and super-resolution, with VIINTER, we show its capability for view interpolation and offer a promising outlook on using INR for image manipulation tasks.

The Nanophotonic Phased Array (NPA) is an emerging holographic display technology. With chip-scaled sizes, high refresh rates, and integrated light sources, a large-scale NPA can enable high-resolution real-time dynamic holographic displays. However, one of the critical challenges impeding the development of such large-scale NPAs is the high electrical power consumption required to modulate the amplitude and phase of each of the pixel elements. We argue that the modulation of all the elements on the array is, in fact, not necessary to produce a high-quality image. We propose a simple method that outputs the configuration of a sparse NPA, along with the amplitude and the phase required at each active pixel to generate the desired image at the observation plane. We identify the set of active pixels according to their optimized intensities. We observe that the brighter pixels have a greater influence on the target image, and it is these that we must focus on in image formation. Using as few as 10% of the total pixels from a dense 2D array of light-emitting elements, we show that a perceptually acceptable holographic image can be generated. We compare various sparse sampling methods through computational simulations and show that our proposed method gives superior qualitative and quantitative results. We believe our study will help advance research on sparse NPAs and facilitate the use of large-scale NPAs to display high-resolution 3D holographic images.

With the speedy increase of display resolution and the demand for interactive frame rate, rendering acceleration is becoming more critical for a wide range of virtual reality applications. Foveated rendering addresses this challenge by rendering with a non-uniform resolution for the display. Motivated by the non-linear optical lens equation, we present rectangular mapping-based foveated rendering (RMFR), a simple yet effective implementation of foveated rendering framework. RMFR supports varying level of foveation according to the eccentricity and the scene complexity. Compared with traditional foveated rendering methods, rectangular mapping-based foveated rendering provides a superior level of perceived visual quality while consuming minimal rendering cost.

We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map representation of 3D objects. Our simple encoder-decoder framework, comprised of a novel identity encoder and class-conditional viewpoint generator, generates 3D consistent depth maps. Our experimental results demonstrate the two-fold advantage of our approach. First, we can directly borrow architectures that work well in the 2D image domain to 3D. Second, we can effectively generate high-resolution 3D shapes with low computational memory. Our quantitative evaluations show that our method is superior to existing depth map methods for reconstructing and synthesizing 3D objects and is competitive with other representations, such as point clouds, voxel grids, and implicit functions. Code and other material will be made available at http://multiview-shapes. umiacs.io.