An L ₁ image transform for edge-preserving smoothing and scene-level intrinsic decomposition

Abstract

a) Original Image (b) Edge-Preserving Smoothing (c) Original Image (d) Edge-Preserving Smoothing (e) Original Image (f) Image Flattening (g) Reflectance (h) Shading (i) Re-TexturingFigure 1: Our algorithm for piecewise image flattening facilitates both edge-preserving smoothing and intrinsic decomposition. Two examples of edge-preserving smoothing are shown in (a)-(d), and one example of intrinsic decomposition is shown in (e)-(h). Intrinsic decomposition enables image editing, such as re-texturing (i). Original images courtesy Flickr users 47765927@N06 (a), 132341054@N03 (c) and 37213589@N08 (e). AbstractIdentifying sparse salient structures from dense pixels is a longstanding problem in visual computing. Solutions to this problem can benefit both image manipulation and understanding. In this paper, we introduce an image transform based on the L1 norm for piecewise image flattening. This transform can effectively preserve and sharpen salient edges and contours while eliminating insignificant details, producing a nearly piecewise constant image with sparse structures. A variant of this image transform can perform edge-preserving smoothing more effectively than existing state-ofthe-art algorithms. We further present a new method for complex scene-level intrinsic image decomposition. Our method relies on the above image transform to suppress surface shading variations, and perform probabilistic reflectance clustering on the flattened image instead of the original input image to achieve higher accuracy. Extensive testing on the Intrinsic-Images-in-the-Wild database indicates our method can perform significantly better than existing techniques both visually and numerically. The obtained intrinsic images have been successfully used in two applications, surface retexturing and 3D object compositing in photographs.

Intrinsic Image Decomposition via Structure-Preserving Image Smoothing and Material Recognition

“…Fig 7 shows a visual comparison between our method and recent methods of [19] and [38] which adopt the sparsity assumption on reflectance. The input image is quite complex due to large shading variations such as highlights and shadows (Fig 7A).…”

“…Fig 7F shows the input image with added brushes. Fig 7B–7D show the reflectance components extracted from our method and methods of [19] and [38], respectively. Three regions are shown distinctly for better visualization.…”

“…As an example, Bi et al [19] used clustering in the CIE-Lab color space and merged the generated clusters based on similarity measures to find regions with similar reflectance. It seems that their approach has two disadvantages: first, clustering generates unconnected image segments that require an additional merging step to find regions with similar reflectance.…”

“…Lambert surface is the general assumption for solving many image processing problems. In the case of intrinsic image decomposition using a single image, since there is no information about lighting conditions and scene geometry, it is not possible to use more complex models and the Lambert assumption has been used frequently in previous methods [2, 6, 19]. …”

“…Secondly, in the case of c 0 and c 1 discontinuity, shading smoothness assumption breaks and leads to undesired clustering of the input image. Bi et al [19] proposed an L 1 image transform for image flattening and used the flattened image to develop a pipeline for intrinsic image decomposition relying on probabilistic boosting trees for reflectance labelling. Utilizing the smooth image for clustering is more desirable compared to clustering the raw input image because of higher probability of associating regions of similar chrominance to reflectance.…”