Researchers at NVIDIA have come up with a clever machine learning technique for taking 2D images and fleshing them out into 3D models. Normally this happens in reverse--these days, it's not all that difficult to take a 3D model and flatten it into a 2D image. But to create a 3D model without feeding a system 3D data is far more challenging. But there's information to be gained from doing the opposite--a model that could infer a 3D object from a 2D image would be able to perform better object tracking, for example.," What the researchers came up with is a rendering framework called DIB-R, which stands for differentiable interpolation-based renderer.
Dec-22-2019, 12:33:06 GMT