Editable Indoor Lighting Estimation
This addresses the challenge for artists and casual users in editing indoor lighting estimates, though it is incremental as it builds on existing methods by enhancing usability.
The paper tackles the problem of estimating realistic indoor lighting from a single image by proposing a method that combines parametric lighting for editability and non-parametric textures for high-frequency details, resulting in interpretable and easily modifiable predictions that produce competitive results.
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.