Deep Parametric Indoor Lighting Estimation
This improves realistic 3D object compositing in indoor scenes, but is incremental as it builds on existing single-image lighting estimation with a new representation.
The paper tackles indoor lighting estimation from a single image by representing lighting as discrete 3D lights with parameters instead of environment maps, and trains a deep network to regress these parameters, achieving more accurate results than previous methods.
We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing correspondences between estimated and ground truth lights. We demonstrate, via quantitative and qualitative evaluations, that our representation and training scheme lead to more accurate results compared to previous work, while allowing for more realistic 3D object compositing with spatially-varying lighting.