Editable Indoor Lighting Estimation
Henrique Weber, Mathieu Garon, Jean-Fran\c{c}ois Lalonde

TL;DR
This paper introduces an interpretable indoor lighting estimation method from a single image, combining parametric and non-parametric components for realistic and editable lighting predictions.
Contribution
It presents a novel pipeline that produces easily editable, realistic indoor lighting estimates with strong shadows and high-frequency details, improving usability for artists and casual users.
Findings
Produces competitive lighting estimation results.
Allows easy editing of lighting parameters.
Combines parametric and non-parametric representations.
Abstract
We present a method for estimating lighting from a single perspective image of an indoor scene. Previous methods for predicting indoor illumination usually focus on either simple, parametric lighting that lack realism, or on richer representations that are difficult or even impossible to understand or modify after prediction. We propose a pipeline that estimates a parametric light that is easy to edit and allows renderings with strong shadows, alongside with a non-parametric texture with high-frequency information necessary for realistic rendering of specular objects. Once estimated, the predictions obtained with our model are interpretable and can easily be modified by an artist/user with a few mouse clicks. Quantitative and qualitative results show that our approach makes indoor lighting estimation easier to handle by a casual user, while still producing competitive results.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Remote Sensing and LiDAR Applications · Color Science and Applications
