SBIR-STTR Award

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will be to make it cheaper and faster for architects, urban planners, and real-estate developers (APDs), as well as many others, to work with detailed models of the real world. Designers in APD fields must visualize and render their projects in the context of the real world. Pictures, videos, 3D printing, and even virtual reality inform the design process and facilitate communication with lay customers and stakeholders. These applications require consistently detailed models of the built world, and this project will automate the generation of these models. We estimate that APDs spend at least $80M annually creating these models by hand; and that at least $300M more is spent on such models for simulations, special effects, and video game design. By algorithmically generating virtual models without human intervention, the significant cost (in time and money) of manual creation will be saved, freeing design professionals to do work they want to be doing. This Small Business Innovation Research (SBIR) Phase I project will advance the state of the art in reconstructing highly detailed models of the world for diverse commercial applications. The first hurdle is solving the problem of reconstructing surfaces representing the boundaries of real-world solids (buildings) from noisy point cloud data. While surface reconstruction is well-studied in a variety of contexts, it remains an open problem in general, as successful algorithms must be informed by priors on the intended datasets. Using a data-driven approach to segment and classify input point clouds will facilitate the application of different reconstruction techniques to different objects (e.g. trees or buildings). The second hurdle is development of a machine learning algorithm which handles the dual problems of procedural modeling and inverse procedural modeling from a single statistical model, enabling visually realistic predictions about the details of a given building, even when that information is not available from source data (which may be of inconsistent quality across a large geographic area).

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is the ability to more completely understand the real world through a perfect virtual copy. This SBIR Phase II project makes it possible to create virtual reproductions of real cities that not only show how the world looks, but reproduce every object and every detail perfectly, allowing users to interact with it. These virtual copies make it possible to quickly and effectively train soldiers and first responders, train autonomous ground and flying vehicles, place new construction into a dense city, simulate the effects of catastrophic weather, and explore imaginary scenarios through games. Billions of dollars are already spent mapping and 3D modeling the real world for these and many other applications, but these virtual cities are created through painstaking manual methods that can take months to years, or lack necessary information about what is in the world. This SBIR Phase II project will make it possible to rapidly and automatically create detailed 3D copies of any area of the real world. This Small Business Innovation Research (SBIR) Phase II project will advance the state of the art in reconstructing highly detailed 3D models of the world for diverse commercial applications. This project introduces new methods for turning raw multimodal sensor data into semantic information describing the world and immersive, interactive-ready 3D models. It will remove the time, money, and manual effort necessary to create accurate 3D models of real world areas today, by using computer intelligence instead of human effort to parse sensor data like photographs and laser scans. The resulting 3D models and underlying semantic information describing the world will be used directly in game engines and simulation software, in analysis tools, in rendering software, and beyond. This research will build on the associated Phase I project, first improving the detail that can be identified and reproduced in virtual copies of the real world, then showing readiness for commercialization with paying customers. The result of the project will be a market-ready product for an initial market segment, capable of accurately reproducing real cities in 3D models that customers can readily use, as well as traction that demonstrates customer need for the product. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.