loading page

Intrinsic Omnidirectional Image Decomposition with Illumination Pre-Extraction
  • RongKai Xu ,
  • Lei Zhang ,
  • Fanglue Zhang
RongKai Xu
Author Profile
Lei Zhang
Beijing Institute of Technology

Corresponding Author:[email protected]

Author Profile
Fanglue Zhang
Author Profile

Abstract

Capturing an omnidirectional image with a 360- degree field of view entails capturing intricate spatial and lighting details of the scene. Consequently, existing intrinsic image decomposition methods face significant challenges when attempting to separate reflectance and shading components from a low dynamic range (LDR) omnidirectional images. To address this, our paper introduces a novel method specifically designed for the intrinsic decomposition of omnidirectional images. Leveraging the unique characteristics of the 360-degree scene representation, we employ a pre-extraction technique to isolate specific illumination information. Subsequently, we establish new constraints based on these extracted details and the inherent characteristics of omnidirectional images. These constraints limit the illumination intensity range and incorporate spherical-based illumination variation. By formulating and solving an objective function that accounts for these constraints, our method achieves a more accurate separation of reflectance and shading components. Comprehensive qualitative and quantitative evaluations demonstrate the superiority of our proposed method over stateof-the-art intrinsic decomposition methods.