RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects

We present RGB-D-Fusion, a multi-modal conditional denoising diffusion probabilistic model to generate high resolution depth maps from low-resolution monocular RGB images of humanoid subjects. RGB-D-Fusion first generates map using an image conditioned and then upsamples the second on RGB-D image. further introduce novel augmentation technique, noise augmentation, increase robustness our super-resolution model.