Abstract | ||
---|---|---|
Estimating a scene's lighting is a very important task when compositing synthetic content within real environments, with applications in mixed reality and post-production. In this work we present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama. In addition to being a challenging and ill-posed problem, the lighting estimation task also suffers from a lack of facile illumination ground truth data, a fact that hinders the applicability of data-driven methods. We approach this problem differently, exploiting the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism. This relies on a global Lambertian assumption that helps us overcome issues related to pre-baked lighting. We relight our training data and complement the model's supervision with a photometric loss, enabled by a differentiable image-based relighting technique. Finally, since we predict spherical spectral coefficients, we show that by imposing a distribution prior on the predicted coefficients, we can greatly boost performance. Code and models available at https://vcl3d.github.io/DeepPanoramaLighting. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CVPRW50498.2020.00328 | CVPR Workshops |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gkitsas Vasileios | 1 | 0 | 0.34 |
Nikolaos Zioulis | 2 | 34 | 10.15 |
Federico Alvarez | 3 | 30 | 7.12 |
Dimitrios Zarpalas | 4 | 303 | 33.96 |
Petros Daras | 5 | 1129 | 131.72 |