Intrinsic image decomposition using focal stacks

Saini, Saurabh; Sakurikar, Parikshit; Narayanan, P. J.

doi:10.1145/3009977.3010046

Cited by 5 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While some approaches consider multiple images as input (from multiple viewpoints [CBLD11, LBP * 12, Laf12, LBD13, HWU * 14, Duc15, XLL * 16], varying illumination [Wei01,MLKS04,Yu16], or different focal distances [SSN16]), images with depth information [BM13, CK13, JCTL14, HGW15], multi-spectral images [SW09], videos [YGL * 14, BST * 14, KGB14, SYC * 14, MZRT16], lightfields [GEZ * 16, AG16] or even videos with depth [LZT * 12], this document focuses on the use of a single RGB image as input, and emphasizes image editing applications. This is motivated by the wide availability of this kind of data and the need for illumination-aware image editing tools.…”

Section: Introductionmentioning

confidence: 99%

Intrinsic Decompositions for Image Editing

Bonneel

Kovács

Paris

et al. 2017

Computer Graphics Forum

View full text Add to dashboard Cite

Figure 1: We evaluate state-of-the-art intrinsic image decomposition algorithms based on their ability to produce seamless, artifact-free results for image edits. To fairly compare different methods, we automatize the image editing process. Left to right, by Poisson-based inpainting of the reflectance layer, we remove a logo on a shirt using the metod of Barron et al. [BM15], we add a picnic blanket over a shadow with the method of Grosse et al. [GJAF09], and add a painting over colored shadows with the method of Bousseau et al. [BPD09]. AbstractIntrinsic 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.

show abstract