Who doesn’t know it? Adobe Photoshop Lightroom Classic CC is a quite popular image editing and digital asset management tool for photographers to improve the quality of their images when using RAW formats by changing properties such as white point, exposure, color and hue. While Adobe Lightroom uses basic GPU acceleration when editing and displaying images in the Viewer, the latest version of Lightroom now also uses GPU-accelerated AI to enhance details.
Using the Sensei AI platform, Adobe engineers trained a neural network to demosaic RAW images, focusing on the problem area of RAW file interpolation. The Detail Enhancement feature uses the RTX Tensor Cores to process RAW files over the neural network (for GPUs without Tensor Cores, this feature uses normal GPU computation). The result is the ability to extract more image details from the original RAW file than is possible with the traditional interpolation method.
Note the significantly improved details in the book and the skin in the knee bend (picture above, click to enlarge) The older Pascal- and Vega-maps do not perform as well in the calculation time.