Intrinsic images using optimization

Shen, Jianbing; Yang, Xiaoshan; Jia, Yingmin; Li, Xuelong

doi:10.1109/cvpr.2011.5995507

Cited by 122 publications

(85 citation statements)

References 18 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over time, "intrinsic images" has become synonymous with the problem that Retinex addressed, that of separating an image into shading and reflectance components [4], [10], [9]. This area has seen seen some recent progress [12], [13], [14], [15], though the performance of Retinex, despite its age, has proven hard to improve upon [4]. The limiting factor in many of these "intrinsic image" algorithms appears to be that they treat "shading" as a kind of image, ignoring the fact that shading is, by construction, the product of some shape and some model of illumination.…”

Section: Prior Workmentioning

confidence: 99%

Shape, Illumination, and Reflectance from Shading

Barron¹,

Malik²

2013

196

420

View full text Add to dashboard Cite

Abstract-A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison -there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint tends to be uniform, and illumination tends to be natural. We therefore pose this problem as one of statistical inference, and define an optimization problem that searches for the most likely explanation of a single image. Our technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.

show abstract

Section: Prior Workmentioning

confidence: 99%

Shape, Illumination, and Reflectance from Shading

Barron¹,

Malik²

2013

196

420

View full text Add to dashboard Cite

show abstract

“…Our intrinsic texture extraction method builds upon the image-based method of Shen et al [26] to incorporate global lighting information and operate over the surface of a mesh. To achieve this, a fast, bilateral filter based intrinsic image decomposition method is introduced.…”

Section: Intrinsic Texture Extraction Filtermentioning

confidence: 99%

“…The contribution of Shen et al [26] is an energy functional, which when minimised splits an image I into its constituent albedo A and shading S images, such that I(x) = A(x)S(x) (equation 11). It is show that this functional can be well approximated using a modified bilateral filter to remove local shading contributions from the original image.…”

Section: Intrinsic Texture Extraction Filtermentioning

confidence: 99%

Intrinsic Textures for Relightable Free-Viewpoint Video

Imber

Guillemaut

Hilton

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. This paper presents an approach to estimate the intrinsic texture properties (albedo, shading, normal) of scenes from multiple view acquisition under unknown illumination conditions. We introduce the concept of intrinsic textures, which are pixel-resolution surface textures representing the intrinsic appearance parameters of a scene. Unlike previous video relighting methods, the approach does not assume regions of uniform albedo, which makes it applicable to richly textured scenes. We show that intrinsic image methods can be used to refine an initial, low-frequency shading estimate based on a global lighting reconstruction from an original texture and coarse scene geometry in order to resolve the inherent global ambiguity in shading. The method is applied to relighting of free-viewpoint rendering from multiple view video capture. This demonstrates relighting with reproduction of fine surface detail. Quantitative evaluation on synthetic models with textured appearance shows accurate estimation of intrinsic surface reflectance properties.

show abstract

“…There has been increasing focus on single-face relighting methods [7], [9], [10], [15]. Li et al decomposed portaits using the logarithm total variation, and replaced the illumination-dependent component of the target with that of the reference [9].…”

Section: Introductionmentioning

confidence: 99%

“…Guo and Sim transferred large changes of gradient in the lighting layer of the reference to the target through Poisson editing [2]. Shen et al employed intrinsic image decomposition [15] for relighting. Chen et al used an adaptive edge-preserving filter and guided filter to transfer illumination [7].…”

Section: Introductionmentioning

confidence: 99%

A New Face Relighting Method Based on Edge-Preserving Filter

Liang

Jin

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe propose a new face relighting method using an illuminance template generated from a single reference portrait. First, the reference is wrapped according to the shape of the target. Second, we employ a new spatially variant edge-preserving smoothing filter to remove the facial identity and texture details of the wrapped reference, and obtain the illumination template. Finally, we relight the target with the template in CIELAB color space. Experiments show the effectiveness of our method for both grayscale and color faces taken from different databases, and the comparisons with previous works demonstrate a better relighting effect produced by our method.

show abstract

Intrinsic images using optimization

Cited by 122 publications

References 18 publications

Shape, Illumination, and Reflectance from Shading

Shape, Illumination, and Reflectance from Shading

Intrinsic Textures for Relightable Free-Viewpoint Video

A New Face Relighting Method Based on Edge-Preserving Filter

Contact Info

Product

Resources

About