Rendering synthetic objects into legacy photographs
A group of students from the University of Illinois at Urbana-Champaign have demonstrated a ground-breaking system that allows a user realistically insert synthetic objects into legacy photographs quickly and easily.
The system requires that the user first annotate an image, pointing out light sources and object boundaries using software-based tools. Once an image in annotated, the system accurately renders synthetic objects placed ‘into’ the photograph, accounting for lighting, shading, reflection, illumination and other individual object properties like transparency, diffuse or specular.
The system has obvious applications in the movie and gaming industry, as well as interior design and user content creation. The video below speaks for itself,
For the past few years, corporate investment into AI startups and in-house R&D have skyrocketed,…
Although we continue to push the frontiers in innovation across healthcare, women remain one of…
The early 2026 mergers and acquisitions (M&A) landscape is supercharged. While the total number of…
Globalists & govts want you to believe that digital ID is unavoidable, to lead you…
A new blockchain-based financial system targeting African economic development is set to to launch at…
As advertising has expanded into a multi-channel revenue model across onsite, offsite, and in-store environments,…
View Comments
very cool! I am assuming the objects would be modeled in a different program and inserted? how are theh new materials scaled/degenerated to match the original image quality? I am interested to follow the development of this program and see the far reaching effects that it can and will have.
very cool! I am assuming the objects would be modeled in a different program and inserted? how are theh new materials scaled/degenerated to match the original image quality? I am interested to follow the development of this program and see the far reaching effects that it can and will have.
very great post.