US 5,850,352 · Granted 1998-12-15

The 1998 Patent That Imagined Virtual Reality Before Smartphones

Imagine watching a sports game from any angle you want—even angles where no camera was actually pointing. This patent describes a system that stitches together video from multiple cameras to let you create and view a scene from positions that never existed in reality, kind of like digital time travel through space.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The claim covers a method for taking multiple video streams shot from different physical locations and processing them through specialized computer software to build a 3D mathematical model of the scene. Once that model exists, the system can generate new 2D video images from any viewpoint the user requests—panoramic views, zoomed-in versions, stereoscopic 3D, or views with apparent motion parallax. What's protected is both the overall process and the specific steps: video analysis, 3D model building, user input interpretation, and final image synthesis from that model.

Why it matters

This patent represents foundational work in synthetic video generation and immersive viewing technology. Filed in 1995 from UC Berkeley and granted in 1998, it emerged during the era when most people still watched TV passively from one fixed angle. The core insight—that you could computationally 'see' a scene from positions where no camera existed—anticipated technologies that would later power virtual reality, sports broadcast enhancements, and 3D reconstruction. It's a conceptual ancestor to modern volumetric capture and view-synthesis systems.

Real-world use

When you watch a modern sports broadcast and see a camera angle that seems to glide smoothly around a player in ways that no single camera could capture, or when VR systems let you look around a reconstructed scene, you're experiencing descendants of the technology this patent describes.

Original USPTO abstract

Immersive video, or television, images of a real-world scene are synthesized, including on demand and/or in real time, as are linked to any of a particular perspective on the scene, or an object or event in the scene. Synthesis is in accordance with user-specified parameters of presentation, including presentations that are any of panoramic, magnified, stereoscopic, or possessed of motional parallax. The image synthesis is based on computerized video processing--called "hypermosaicing"--of multiple video perspectives on the scene. In hypermosaicing a knowledge database contains information about the scene; for example scene geometry, shapes and behaviors of objects in the scene, and/or internal and/or external camera calibration models. Multiple video cameras each at a different spatial location produce multiple two-dimensional video images of the scene. A viewer/user specifies viewing criterion (ia) at a viewer interface. A computer, typically one or more engineering work station class computers or better, includes in software and/or hardware (i) a video data analyzer for detecting and for tracking scene objects and their locations, (ii) an environmental model builder combining multiple scene images to build a 3D dynamic model recording scene objects and their instant spatial locations, (iii) a viewer criterion interpreter, and (iv) a visualizer for generating from the 3D model in accordance with the viewing criterion one or more selectively synthesized 2D video image(s) of the scene.

Patent details

Publication number: US 5,850,352
Filing date: 1995-11-06
Grant date: 1998-12-15
Assignee: The Regents Of The University Of California
Inventor(s): MOEZZI; SAIED, KATKERE; ARUN, JAIN; RAMESH
CPC class: G06T15/10

View original record on Google Patents →

Want to file your own patent?

If you're building the next generation of immersive media or virtual viewing platform, search our database to see what patents already guard this creative space.

Free patentability scan