Recovering intrinsic images from a single image

Tappen, Marshall F.; Freeman, William T.; Adelson, Edward H.

doi:10.1109/tpami.2005.185

Cited by 356 publications

(319 citation statements)

References 21 publications

Supporting

Mentioning

315

Contrasting

Unclassified

Order By: Relevance

“…The problem of estimating albedo and lighting from an image, without knowledge of geometry, has been extensively studied in computer vision as the problem of intrinsic image extraction [12][13][14][15]. The interaction of physical objects with light is governed by its intrinsic colours (albedo), specular properties, transmission properties and surface normals.…”

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

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

show abstract

“…[Step 2 : Hard constraints] Apply the inter-frame and inter-pixel constraints expressed in (10). Since it is difficult to minimize the two terms in (10) simultaneously, we employ an iterative approach for minimization.…”

Section: [Smoothness Constraints]mentioning

confidence: 99%

“…Instead of relying on smoothness constraints, Tappen et al [10] proposed a learning-based approach to separate reflectance edges and illumination edges in a derivative image. Although this method successfully separates reflectance and shading for a given illumination direction used in training, it is difficult to create such a prior to classify edges under arbitrary lighting.…”

Section: Introductionmentioning

confidence: 99%

Estimating Intrinsic Images from Image Sequences with Biased Illumination

Matsushita

Lin

Kang

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We present a method for estimating intrinsic images from a fixed-viewpoint image sequence captured under changing illumination directions. Previous work on this problem reduces the influence of shadows on reflectance images, but does not address shading effects which can significantly degrade reflectance image estimation under the typically biased sampling of illumination directions. In this paper, we describe how biased illumination sampling leads to biased estimates of reflectance image derivatives. To avoid the effects of illumination bias, we propose a solution that explicitly models spatial and temporal constraints over the image sequence. With this constraint network, our technique minimizes a regularization function that takes advantage of the biased image derivatives to yield reflectance images less influenced by shading.

show abstract

“…Other features like edge (Li et al, 2006;Salvador et al, 2001), histograms (Finlayson et al, 2005), texture (Leone and Distante, 2007), geometry property (Salvador et al, 2004), color ratios (Barnard and Finlayson, 2000), and gradient The present work was supported by Natural Science Foundation of China (Grant Number: 60871078 and 60835004). (Ravi et al, 2007;Tappen et al, 2005) are also widely used. Compared with model-based approaches, property-based algorithms shows more robustness when the scene and illumination conditions change (Bevilacqua, 2006).…”

Section: Introductionmentioning

confidence: 99%

Retinex theory‐based shadow detection and removal in single outdoor image

Sun

Tian

et al. 2009

Industrial Robot: An International Journal

View full text Add to dashboard Cite

Purpose -Shadows, the common phenomena in most outdoor scenes, bring many problems in practical image processing. Shadow detection and removal, especial in uncalibrated outdoor image, is still a difficult problem. The purpose of this paper is to detect and to remove shadows in single outdoor image based on retinex theory. Design/methodology/approach -The shadow extraction algorithm originates from a simple idea that the human-vision-based retinex has the natural ability to enhance the shadow regions of an image no matter it is penumbrae or umbrae. Shadows are detected by comparing the retinexenhanced images with original images in the paper. The shadow removal algorithm in the paper deals with the shadow regions and non-shadow regions in the images separately using the retinex enhancement algorithm. Through adding smooth light forcibly to shadow edges and introducing shadow edge masks, the authors reduce the effects of shadow edges in shadow removal processing. Findings -Some real single outdoor images with the umbra regions and those with penumbra regions are both experimented in the paper. Experimental results validate the feasibility of the approach. Originality/value -The approach proposed here does not use any special prior knowledge and assumptions. The feasibility of this method is testified for detecting and removing both penumbrae and umbrae in the outdoor images.

show abstract

Recovering intrinsic images from a single image

Cited by 356 publications

References 21 publications

Intrinsic Textures for Relightable Free-Viewpoint Video

Intrinsic Textures for Relightable Free-Viewpoint Video

Estimating Intrinsic Images from Image Sequences with Biased Illumination

Retinex theory‐based shadow detection and removal in single outdoor image

Contact Info

Product

Resources

About