Traditionally, reproduction of a real-world object in the VR/AR environment, we need to replicate the 3D geometry and appearance of the object.
And this has been either done manually by 3D artists, which is a labour-intensive task, or by using specialized, expensive hardware.



Min H. Kim, associate professor of computer science at KAIST in South Korea and his collaborators, Diego Gutierrez, professor of computer science at Universidad de Zaragoza in Spain, and KAIST PhD students Giljoo Nam and Joo Ho Lee has developed  a straightforward, cheaper and efficient way to reproduces realistic 3D objects by just taking photos from a single camera with a built-in flash.
The world has already seen the reproduction of real-life objects in 3D.
But the existing approaches for the acquisition of physical objects require specialized hardware setups to achieve geometry and appearance modelling of the desired objects.
Those setups might include a 3D laser scanner or multiple cameras, or a lighting dome with more than a hundred light sources.
This made the process very expensive and time-consuming.



"In contrast, this new technique only needs a single camera, to produce high-quality outputs."

There are traditional methods to achieve this feat by using a single camera
But these can capture only the 3D geometry of objects, but not the complex reflectance of real-world objects, given by the SVBRDF. (spatially-varying bidirectional reflectance distribution functions, which is key in obtaining an object's real-world shape and appearance)


Mr Kim and his group successfully presented this new work at SIGGRAPH Asia 2018 in Tokyo from 4 December to 7 December.
The group demonstrated their framework using a digital camera, the Nikon D7000 and the built-in camera of an Android mobile phone.
Their paper had the title: "Practical SVBRDF Acquisition of 3D Objects with Unstructured Flash Photography."
The novel algorithm, which does not require any input geometry of the target object, successfully captured the geometry and appearance of 3D objects with basic, flash photography and reproduced consistent results. The algorithm was a success for the computer science world had made a huge contribution to the advancement of technology.


In the future, the researchers target to simplify down the capturing process and will be trying to include the dynamic geometry for larger objects.