Intrinsic Decompositions for Image Editing

Nicolas Bonneel 1, 2 Balazs Kovacs Sylvain Paris 3 Kavita Bala
1 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 GeoMod - Modélisation Géométrique, Géométrie Algorithmique, Fractales
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Intrinsic images are a mid-level representation of an image that decompose the image into reflectance and illumination layers. The reflectance layer captures the color/texture of surfaces in the scene, while the illumination layer captures shading effects caused by interactions between scene illumination and surface geometry. Intrinsic images have a long history in computer vision and recently in computer graphics, and have been shown to be a useful representation for tasks ranging from scene understanding and reconstruction to image editing. In this report, we review and evaluate past work on this problem. Specifically, we discuss each work in terms of the priors they impose on the intrinsic image problem. We introduce a new synthetic ground-truth dataset that we use to evaluate the validity of these priors and the performance of the methods. Finally, we evaluate the performance of the different methods in the context of image-editing applications.
Complete list of metadatas

Cited literature [67 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01483773
Contributor : Nicolas Bonneel <>
Submitted on : Monday, March 6, 2017 - 2:24:55 PM
Last modification on : Monday, June 10, 2019 - 1:19:02 AM
Long-term archiving on : Wednesday, June 7, 2017 - 2:04:06 PM

File

star-intrinsic_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01483773, version 1

Citation

Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, Kavita Bala. Intrinsic Decompositions for Image Editing. Computer Graphics Forum, Wiley, 2017, Eurographics State of the Art Reports 2017, 36 (2), pp.593-609. ⟨hal-01483773⟩

Share

Metrics

Record views

381

Files downloads

138