International Conference on Computer Vision, Theory and Applications (VISAPP 2025)
Editing Scene Illumination and Material Appearance of Light-Field Images
Jaemin Cho
Dongyoung Choi
Dahyun Kang
Gun Bang
Min H. Kim
KAIST
ETRI
We present a method to decompose light-field images
into illumination and intrinsic appearance parameters,
enabling realistic relighting and material editing. Refer to
our supplemental video for additional results.
Supplemental video results
Abstract
In this paper, we propose a method for editing the scene appearance of light-field images. Our method enables
users to manipulate the illumination and material properties of scenes captured in light-field format, offering
various control over image appearance, including dynamic relighting and material appearance modification,
which leverages our specially designed inverse rendering framework for light-field images. By effectively
separating light fields into appearance parameters—such as diffuse albedo, normal, specular intensity, and
roughness within a multi-plane image domain, we overcome the traditional challenges of light-field imaging
decomposition. These challenges include handling front-parallel views and a limited image count, which
have previously hindered neural inverse rendering networks when applying them to light-field image data.
Our method also approximates environmental illumination using spherical Gaussians, significantly enhancing
the realism of scene reflectance. Furthermore, by differentiating scene illumination into far-bound and nearbound
light environments, our method enables highly realistic editing of scene appearance and illumination,
especially for local illumination effects. This differentiation allows for efficient, real-time relighting rendering
and integrates seamlessly with existing layered light-field rendering frameworks. Our method demonstrates
rendering capabilities from casually captured light-field images.
BibTeX
@InProceedings{Cho:visapp:2025,
author = {Jaemin Cho and Dongyoung Choi and Dahyun Kang and
Gun Bang and Min H. Kim},
title = {Editing Scene Illumination and Material Appearance
of Light-Field Images},
booktitle = {Proc. Int. Conf. Computer Vision,
Theory and Applications (VISAPP 2025)},
address = {Porto, Portugal},
year = {2025},
pages = {},
}
