User-assisted intrinsic images

Bousseau, Adrien; Paris, Sylvain; Durand, Frédo

doi:10.1145/1618452.1618476

Cited by 178 publications

(171 citation statements)

References 27 publications

Supporting

Mentioning

164

Contrasting

Order By: Relevance

“…Two recent methods [9,10] include in their optimization user-provided local constraints: constant-reflectance, constant-illumination and fixed-illumination. In single-image modelling, Zhang et al [11] optimize for a mesh satisfying user-provided normal, positional and curvature constraints.…”

Section: Related Workmentioning

confidence: 99%

User Directed Multi-view-stereo

Doron

Campbell

Starck

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Depth reconstruction from video footage and image collections is a fundamental part of many modelling and image-based rendering applications. However real-world scenes often contain limited texture information, repeated elements and other ambiguities which remain challenging for fully automatic algorithms. This paper presents a technique that combines intuitive user constraints with dense multi-view stereo reconstruction. By providing annotations in the form of simple paint strokes, a user can guide a multi-view stereo algorithm and avoid common failure cases. We show how smoothness, discontinuity and depth ordering constraints can be incorporated directly into a variational optimization framework for multi-view stereo. Our method avoids the need for heuristic approaches that edit a depth-map in a sequential process, and avoids requiring the user to accurately segment object boundaries or to directly model geometry. We show how with a small amount of intuitive input, a user may create improved depth maps in challenging cases for multi-view-stereo.

show abstract

Section: Related Workmentioning

confidence: 99%

User Directed Multi-view-stereo

Doron

Campbell

Starck

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…For example, Bousseau et al [16] has a user interact with the system to guide the process, whereas Barron and Malik [17] use a set of shape and albedo priors based on general localised properties of natural images.…”

Section: Intrinsic Image Extractionmentioning

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

“…Further, for colour balancing and correction, Hsu et al [2] recovered a set of dominant material colours to estimate the local mixture coefficients of the lights. Recently, several authors proposed methods for white balance under mixed lighting conditions using user-assisted inputs and sparse interpolation [10], [11].…”

Section: Introductionmentioning

confidence: 99%

“…Secondly, our method does not require user-intervention. Being completely unsupervised sets it apart from methods such as those in [10], [11]. In addition, unlike the work in [20], the illumination colour can be segmented without sampling image patches.…”

Section: Introductionmentioning

confidence: 99%

Segmentation and Estimation of Spatially Varying Illumination

Huynh

Robles-Kelly

2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we present an unsupervised method for segmenting the illuminant regions and estimating the illumination power spectrum from a single image of a scene lit by multiple light sources. Here, illuminant region segmentation is cast as a probabilistic clustering problem in the image spectral radiance space. We formulate the problem in an optimisation setting which aims to maximise the likelihood of the image radiance with respect to a mixture model while enforcing a spatial smoothness constraint on the illuminant spectrum. We initialise the sample pixel set under each illuminant via a projection of the image radiance spectra onto a low-dimensional subspace spanned by a randomly chosen subset of spectra. Subsequently, we optimise the objective function in a coordinateascent manner by updating the weights of the mixture components, the sample pixel set under each illuminant and the illuminant posterior probabilities. We then estimate the illuminant power spectrum per pixel making use of these posterior probabilities. We compare our method with a number of alternatives for the tasks of illumination region segmentation, illumination colour estimation and colour correction. Our experiments show the effectiveness of our method as applied to one hyperspectral and three trichromatic image datasets.

show abstract

User-assisted intrinsic images

Cited by 178 publications

References 27 publications

User Directed Multi-view-stereo

User Directed Multi-view-stereo

Intrinsic Textures for Relightable Free-Viewpoint Video

Segmentation and Estimation of Spatially Varying Illumination

Contact Info

Product

Resources

About