EMLight: Lighting Estimation via Spherical Distribution Approximation
This work provides a more accurate illumination estimation method for computer graphics practitioners and researchers working on 3D rendering and relighting, addressing issues with existing methods' optimization and prediction accuracy.
This paper tackles the problem of illumination estimation from a single image for 3D rendering. The authors propose EMLight, a framework that decomposes illumination into spherical light distribution, light intensity, and an ambient term, and uses a novel spherical mover's loss. EMLight achieves accurate illumination estimation and generates more plausible and faithful relighting in 3D object embedding compared to state-of-the-art methods.
Illumination estimation from a single image is critical in 3D rendering and it has been investigated extensively in the computer vision and computer graphic research community. On the other hand, existing works estimate illumination by either regressing light parameters or generating illumination maps that are often hard to optimize or tend to produce inaccurate predictions. We propose Earth Mover Light (EMLight), an illumination estimation framework that leverages a regression network and a neural projector for accurate illumination estimation. We decompose the illumination map into spherical light distribution, light intensity and the ambient term, and define the illumination estimation as a parameter regression task for the three illumination components. Motivated by the Earth Mover distance, we design a novel spherical mover's loss that guides to regress light distribution parameters accurately by taking advantage of the subtleties of spherical distribution. Under the guidance of the predicted spherical distribution, light intensity and ambient term, the neural projector synthesizes panoramic illumination maps with realistic light frequency. Extensive experiments show that EMLight achieves accurate illumination estimation and the generated relighting in 3D object embedding exhibits superior plausibility and fidelity as compared with state-of-the-art methods.