PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing
This addresses the challenge of making synthetic images more realistic for applications in computer graphics and visual effects, though it is incremental over prior deep learning methods.
The paper tackles the problem of generating realistic lighting effects like shadows and reflections in 2D image compositing by introducing PixHt-Lab, which uses a pixel height mapping to 3D space to reconstruct geometry and render diverse effects, resulting in significant improvements in soft shadow generation as shown in evaluations.
Lighting effects such as shadows or reflections are key in making synthetic images realistic and visually appealing. To generate such effects, traditional computer graphics uses a physically-based renderer along with 3D geometry. To compensate for the lack of geometry in 2D Image compositing, recent deep learning-based approaches introduced a pixel height representation to generate soft shadows and reflections. However, the lack of geometry limits the quality of the generated soft shadows and constrain reflections to pure specular ones. We introduce PixHt-Lab, a system leveraging an explicit mapping from pixel height representation to 3D space. Using this mapping, PixHt-Lab reconstructs both the cutout and background geometry and renders realistic, diverse, lighting effects for image compositing. Given a surface with physically-based materials, we can render reflections with varying glossiness. To generate more realistic soft shadows, we further propose to use 3D-aware buffer channels to guide a neural renderer. Both quantitative and qualitative evaluations demonstrate that PixHt-Lab significantly improves soft shadow generation.