Surface-from-Gradients with Incomplete Data for Single View Modeling

Ng, Heung-Sun; Wu, Tong; Tang, Chi-Keung

doi:10.1109/iccv.2007.4409103

Cited by 8 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work is most closely related to [van Overveld 1996], [Bourguignon et al 2004], [Kerautret et al 2005], and Ng et al 2007]. …”

Section: Related Workmentioning

confidence: 94%

“…introduces a paradigm for modeling shapes by transferring normal information from a a reference shape (shape palette) to the modeled height field. [Ng et al 2007] describes a method for recovering a surface from dense or sparse normal information using radial basis functions in a variational context, without restricting the resulting surface to be a height field, also found to be essential in our context.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Shading-based surface editing

Gingold

Zorin

2008

ACM Trans. Graph.

View full text Add to dashboard Cite

We present a system for free-form surface modeling that allows a user to modify a shape by changing its rendered, shaded image using stroke-based drawing tools. User input is translated into a set of tangent and positional constraints on the surface. A new shape, whose rendered image closely approximates user input, is computed using an efficient and stable surface optimization procedure. We demonstrate how several types of free-form surface edits which may be difficult to cast in terms of standard deformation approaches can be easily performed using our system.

show abstract

“…Our work is most closely related to [van Overveld 1996], [Bourguignon et al 2004], [Kerautret et al 2005], and Ng et al 2007]. …”

Section: Related Workmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Shading-based surface editing

Gingold

Zorin

2008

ACM Trans. Graph.

View full text Add to dashboard Cite

show abstract

“…It is written in [40] that the accuracy of Frankot and Chellappa's method "relies on a good input scale". In fact, it only happens that, in a publicly available code of this method, the 2π coefficient in (38) is missing.…”

Section: Frankot and Chellappa's Methodsmentioning

confidence: 99%

“…Replacing any term in (30) by its inverse discrete Fourier transform of the form (40), and knowing that the Fourier family is a basis, we obtain: 2 cos 2π k m + cos 2π l n − 2 ẑ k,l = j sin 2π k m p k,l + sin 2π l n q k,l…”

Section: Improvements Of Frankot and Chellappa's Methodsmentioning

confidence: 99%

Normal Integration: A Survey

Quéau¹,

2017

View full text Add to dashboard Cite

The need for efficient normal integration methods is driven by several computer vision tasks such as shape-from-shading, photometric stereo, deflectometry, etc. In the first part of this survey, we select the most important properties that one may expect from a normal integration method, based on a thorough study of two pioneering works by Horn and Brooks [28] and by Frankot and Chellappa [19]. Apart from accuracy, an integration method should at least be fast and robust to a noisy normal field. In addition, it should be able to handle several types of boundary condition, including the case of a free boundary, and a reconstruction domain of any shape i.e., which is not necessarily rectangular. It is also much appreciated that a minimum number of parameters have to be tuned, or even no parameter at all. Finally, it should preserve the depth discontinuities. In the second part of this survey, we review most of the existing methods in view of this analysis, and conclude that none of them satisfies all of the required properties. This work is complemented by a companion paper entitled Variational Methods for Normal Integration, in which we focus on the problem of normal integration in the presence of depth discontinuities, a problem which occurs as soon as there are occlusions.

show abstract

“…An early example is given by Horn for shape-from-shading, in the form of a term that minimizes the difference between the reflectance map and image irradiance, along with the surface gradient [13]. Several papers combine depth information with normals to improve depth map reconstruction [14][15][16]. Lischinski et al [17] apply strokes as data constraints for gradient-based scattered data interpolation.…”

Section: Related Workmentioning

confidence: 99%

Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems

Bhat

Curless

Cohen

et al. 2008

Lecture Notes in Computer Science

100

View full text Add to dashboard Cite

Abstract. We analyze the problem of reconstructing a 2D function that approximates a set of desired gradients and a data term. The combined data and gradient terms enable operations like modifying the gradients of an image while staying close to the original image. Starting with a variational formulation, we arrive at the "screened Poisson equation" known in physics. Analysis of this equation in the Fourier domain leads to a direct, exact, and efficient solution to the problem. Further analysis reveals the structure of the spatial filters that solve the 2D screened Poisson equation and shows gradient scaling to be a well-defined sharpen filter that generalizes Laplacian sharpening, which itself can be mapped to gradient domain filtering. Results using a DCT-based screened Poisson solver are demonstrated on several applications including image blending for panoramas, image sharpening, and de-blocking of compressed images.

show abstract

Surface-from-Gradients with Incomplete Data for Single View Modeling

Abstract: Abstract

Cited by 8 publications

References 28 publications

Shading-based surface editing

Shading-based surface editing

Normal Integration: A Survey

Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems

Contact Info

Product

Resources

About