Deep Sky Modeling for Single Image Outdoor Lighting Estimation

We propose a data-driven learned sky model, which we use for outdoor lighting estimation from a single image. As no large-scale dataset of images and their corresponding ground truth illumination is readily available, we use complementary datasets to train our approach, combining the vast diversity of illumination conditions of SUN360 with the radiometrically calibrated and physically accurate Laval HDR sky database. Our key contribution is to provide a holistic view of both lighting modeling and estimation, solving both problems end-to-end. From a test image, our method can directly estimate an HDR environment map of the lighting without relying on analytical lighting models. We demonstrate the versatility and expressivity of our learned sky model and show that it can be used to recover plausible illumination, leading to visually pleasant virtual object insertions. To further evaluate our method, we capture a dataset of HDR 360° panoramas and show through extensive validation that we significantly outperform previous state-of-the-art.


Yannick Hold-Geoffroy, Akshaya Athawale, and Jean-Fran├žois Lalonde
Deep Sky Modeling for Single Image Outdoor Lighting Estimation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[arXiv pre-print] [BibTeX]

Supplementary material

We provide additional results in this supplementary page.


Laval Outdoor HDR Dataset

The Outdoor HDR ULaval dataset used in this publication is available at

SUN360-HDR dataset

We present the SUN360-HDR dataset, which contains HDR outdoor panoramas from the original SUN360 dataset at 64x128 resolution in EXR format. The HDR has been extrapolated using the technique presented in our ICCV 2017 paper.

Because of restrictions imposed by the original SUN360 dataset, the SUN360-HDR dataset is available strictly for research purposes. Please contact Jean-Francois Lalonde at jflalonde at gel dot ulaval dot ca to obtain the dataset.


You can download the slides presented at CVPR 2019 here.

Keynote Powerpoint


The authors gratefully acknowledge the following funding sources:

  • A generous donation from Adobe to Jean-Francois Lalonde
  • NVIDIA Corporation with the donation of the Titan X GPU used for this research.
  • NSERC Discovery GRANT RGPIN-2014-05314
  • REPARTI Strategic Network

Ulaval logo
Adobe logo