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

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. Accurately representing the human body in 3D is a very active research field given its wide variety of appl...

Full description

Bibliographic Details
Main Authors: Sascha Kirch, Valeria Olyunina, Jan Ondrej, Rafael Pages, Sergio Martin, Clara Perez-Molina
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Diffusion models
generative deep learning
monocular depth estimation
depth super-resolution
multi-modal
augmented-reality
Online Access:https://ieeexplore.ieee.org/document/10239167/

Internet

https://ieeexplore.ieee.org/document/10239167/

Similar Items