LightPainter: Interactive Portrait Relighting with Freehand Scribble
This addresses the need for more user-friendly and controllable portrait lighting editing tools for artists and photographers, representing an incremental improvement over existing methods.
The paper tackles the problem of intuitive and precise lighting control in portrait relighting by introducing LightPainter, a scribble-based system that enables interactive manipulation, achieving high-quality results as demonstrated through quantitative and qualitative experiments and user preference in comparisons with commercial tools.
Recent portrait relighting methods have achieved realistic results of portrait lighting effects given a desired lighting representation such as an environment map. However, these methods are not intuitive for user interaction and lack precise lighting control. We introduce LightPainter, a scribble-based relighting system that allows users to interactively manipulate portrait lighting effect with ease. This is achieved by two conditional neural networks, a delighting module that recovers geometry and albedo optionally conditioned on skin tone, and a scribble-based module for relighting. To train the relighting module, we propose a novel scribble simulation procedure to mimic real user scribbles, which allows our pipeline to be trained without any human annotations. We demonstrate high-quality and flexible portrait lighting editing capability with both quantitative and qualitative experiments. User study comparisons with commercial lighting editing tools also demonstrate consistent user preference for our method.