Abstract | ||
---|---|---|
We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting. We show that this can be accomplished in a three step process: 1) we train a robust lighting classifier to automatically annotate the location of light sources in a large dataset of LDR environment maps, 2) we use these annotations to train a deep neural network that predicts the location of lights in a scene from a single limited field-of-view photo, and 3) we fine-tune this network using a small dataset of HDR environment maps to predict light intensities. This allows us to automatically recover high-quality HDR illumination estimates that significantly outperform previous state-of-the-art methods. Consequently, using our illumination estimates for applications like 3D object insertion, produces photo-realistic results that we validate via a perceptual user study.
|
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3130800.3130891 | ACM Trans. Graph. |
Keywords | DocType | Volume |
deep learning, indoor illumination | Journal | abs/1704.00090 |
Issue | ISSN | Citations |
6 | 0730-0301 | 34 |
PageRank | References | Authors |
1.27 | 19 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marc-André Gardner | 1 | 222 | 11.20 |
Kalyan Sunkavalli | 2 | 500 | 31.75 |
Ersin Yumer | 3 | 187 | 8.36 |
Xiaohui Shen | 4 | 1278 | 50.50 |
Emiliano Gambaretto | 5 | 34 | 1.27 |
Christian Gagné | 6 | 627 | 52.38 |
Jean-françois Lalonde | 7 | 590 | 37.69 |