A team of NVIDIA researchers, led by research scientist Guilin Liu, created an impressive AI deep learning method that can reconstruct photos with realistic results. The process is called “image inpainting.”
The method, which performs a process called “image inpainting”, could be implemented in photo editing software to remove unwanted content, while filling it with a realistic computer-generated alternative.
“Our model can robustly handle holes of any shape, size location, or distance from the image borders. Previous deep learning approaches have focused on rectangular regions located around the center of the image, and often rely on expensive post-processing.” (read more)