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,
We often hear that a sedentary lifestyle is the new smoking. As an increasing percentage…
The UN compliance portal is about making sure govts work with the private sector to…
For most of humanity’s 2.8 million-year existence, life expectancy barely budged. But, over the last…
Cui bono? If AI were to become a religion, then the Priests, Imams, Rabbis, and…
Throughout the course of 2025, we’ve seen a huge uptick in the number of countries…
The US spy community's research and development funding arm IARPA announces the B-SAURUS program to…
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.