SIR-Net: Self-Supervised Transfer for Inverse Rendering via Deep Feature Fusion and Transformation From a Single Image

SIR-Net: Self-Supervised Transfer for Inverse Rendering via Deep Feature Fusion and Transformation From a Single Image

Measuring the material, geometry, and ambient lighting of surfaces is a key technology in the object's appearance reconstruction. In this article, we propose a novel deep learning-based method to extract such information to reconstruct the object's appearance from an RGB image. Firstly, we...

Full description

Bibliographic Details
Main Authors: Tianteng Bi, Junjie Ma, Yue Liu, Dongdong Weng, Yongtian Wang
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Inverse rendering
attention
feature fusion
lighting recovery
material estimation
deep learning
Online Access:https://ieeexplore.ieee.org/document/9246498/

Internet

https://ieeexplore.ieee.org/document/9246498/

Similar Items