NVIDIA Uses Machine Learning to Extract 3D Models from 2D Images
<p>NVIDIA has published research demonstrating the use of machine learning to infer a 3D model from a single 2D image. From the <a href=https://blogs.nvidia.com/blog/2019/12/09/neurips-research-3d/ target=_blank>blog</a>:</p><blockquote>In traditional computer graphics, a pipeline renders a 3D model to a 2D screen. 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.<br><br>NVIDIA researchers wanted to build an architecture that could do this while integrating seamlessly with machine learning techniques. The result, DIB-R, produces high-fidelity rendering by using an encoder-decoder architecture, a type of neural network that transforms input into a feature map or vector that is used to predict specific information such as shape, color, texture and lighting of an image.</blockquote><p>The paper, "Learning to Predict 3D Objects with an Interpolation-Based Renderer" is available <a href=https://nv-tlabs.github.io/DIB-R/files/diff_shader.pdf target=_blank>here</a>.</p><p class=ql-align-center><br></p>
Discussion