Figure 1: Example output from our reconstruction system without any geometry post-processing. Scene is about 20m wide and 4m high and captured online in less than 5 minutes with live feedback of the reconstruction. Online 3D reconstruction is gaining newfound interest due to the availability of real-time consumer depth cameras. The basic problem takes live overlapping depth maps as input and incrementally fuses these into a single 3D model. This is challenging particularly when real-time performance is desired without trading quality or scale. We contribute an online system for large and fine scale volumetric recon-struction based on a memory and speed efficient data structure. Our system uses a simple spatial hashing scheme that compresses space, and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure. Sur-face data is only stored densely where measurements are observed. Additionally, data can be streamed efficiently in or out of the hash table, allowing for further scalability during sensor motion. We show interactive reconstructions of a variety of scenes, reconstructing both fine-grained details and large scale environments. We illustrate how all parts of our pipeline from depth map pre-processing, camera pose estimation, depth map fusion, and surface rendering are performed at real-time rates on commodity graphics hardware. We conclude with a comparison to current state-of-the-art online systems, illustrating improved performance and reconstruction quality.

and 65 lights (16ms). Recently, several algorithms have been introduced that enable real-time performance for many lights in applications such as games. In this paper, we explore the use of hardware-supported virtual cube-map shadows to efficiently implement high-quality shadows from hundreds of light sources in real time and within a bounded memory footprint. In addition, we explore the utility of ray tracing for shad-ows from many lights and present a hybrid algorithm combining ray tracing with cube maps to exploit their respective strengths. Our solution supports real-time performance with hundreds of lights in fully dynamic high-detail scenes.

Figure 1: An example of using our algorithm to evaluate precomputed shadows from the sun when viewing the scene at varying scales. Our compact data structure occupies 100MB of graphics memory and is equivalent to a 256k×256k (i.e. 2621442) shadow map. With a filter size of 9×9 taps, shadow evaluation is done in < 1ms at 1080p resolution. Producing high-quality shadows in large environments is an im-portant and challenging problem for real-time applications such as games. We propose a novel data structure for precomputed shadows, which enables high-quality filtered shadows to be reconstructed for any point in the scene. We convert a high-resolution shadow map to a sparse voxel octree, where each node encodes light visibility for the corresponding voxel, and compress this tree by merging common subtrees. The resulting data structure can be many orders of magnitude smaller than the corresponding shadow map. We also show that it can be efficiently evaluated in real time with large filter kernels.