A Non-local Approach to Shape from Ambient Shading

Prados, Emmanuel; Jindal, Nihar; Soatto, Stefano

doi:10.1007/978-3-642-02256-2_58

Cited by 10 publications

(6 citation statements)

References 19 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ambient) continuous field of illumination was studied by Prados et al [27] who demonstrated that shading under such illumination can be ambiguous. Allowing arbitrary illumination but neglecting occlusions, the most general approach is due to Basri et al [28].…”

Section: Related Workmentioning

confidence: 99%

Height from photometric ratio with model-based light source selection

Smith

Fang

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

In this paper, we present a photometric stereo algorithm for estimating surface height. We follow recent work that uses photometric ratios to obtain a linear formulation relating surface gradients and image intensity. Using smoothed finite difference approximations for the surface gradient, we are able to express surface height recovery as a linear least squares problem that is large but sparse. In order to make the method practically useful, we combine it with a model-based approach that excludes observations which deviate from the assumptions made by the image formation model. Despite its simplicity, we show that our algorithm provides surface height estimates of a high quality even for objects with highly non-Lambertian appearance. We evaluate the method on both synthetic images with ground truth and challenging real images that contain strong specular reflections and cast shadows.

show abstract

Section: Related Workmentioning

confidence: 99%

Height from photometric ratio with model-based light source selection

Smith

Fang

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…Prados et al [104] have shown how shading caused by occlusion under perfectly ambient illumination can be used to estimate 3D shape. In this thesis we take a step towards incorporating global illumination effects into the inverse rendering process.…”

Section: Global Shadingmentioning

confidence: 99%

“…Langer and Zucker [70] were the first to study the problem from a computational perspective. More recently, Prados et al [104] showed that the problem is ill-posed under certain conditions (see Figure 5.11) and amounts to the solution of a strongly non-local and non-linear Integro-Partial Differential Equation.…”

Section: Shape From Ambient Occlusionmentioning

confidence: 99%

Inverse Rendering of Faces with a 3D Morphable Model

Aldrian

Smith

2013

IEEE Trans. Pattern Anal. Mach. Intell.

176

160

View full text Add to dashboard Cite

In this thesis, we present a complete framework to inverse render faces with a 3D Morphable Model. By decomposing the image formation process into a geometric and photometric part, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a globally optimal solution can be found. We start by recovering 3D shape using a novel algorithm which incorporates generalisation errors of the model obtained from empirical measurements. The algorithm is extended so it can efficiently deal with mixture distributions. We then describe three methods to recover facial texture, and for the second and third, diffuse lighting, specular reflectance and camera properties from a single image. These methods make increasingly weak assumptions and can all be solved in a linear fashion. We further modify our framework so it accounts for global illumination effects. This is achieved by incorporating statistical models for ambient occlusion and bent normals into the image formation model. We show that solving for ambient occlusion and bent normal parameters as part of the fitting process improves the accuracy of the estimated texture map and illumination environment. We present results on challenging data, rendered under complex natural illumination with both specular reflectance and occlusion of the illumination environment. We evaluate our findings on publicly available datasets, where we are able to obtain state-ofthe-art results. Finally, we present a practical method to synthesise a larger population from a small training-set and show how the new instances can be used to build a flexible PCA model.

show abstract

“…Finally, our work is also related to methods that recover shape from AO [17,21], and our algorithm could potentially be used to generate inputs to such methods.…”

Section: Related Workmentioning

confidence: 99%

Photometric Ambient Occlusion

Hauagge

Wehrwein

Bala

et al. 2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We present a method for computing ambient occlusion (AO) for a stack of images of a scene from a fixed viewpoint. Ambient occlusion, a concept common in computer graphics, characterizes the local visibility at a point: it approximates how much light can reach that point from different directions without getting blocked by other geometry. While AO has received surprisingly little attention in vision, we show that it can be approximated using simple, per-pixel statistics over image stacks, based on a simplified image formation model. We use our derived AO measure to compute reflectance and illumination for objects without relying on additional smoothness priors, and demonstrate state-of-the art performance on the MIT Intrinsic Images benchmark. We also demonstrate our method on several synthetic and real scenes, including 3D printed objects with known ground truth geometry.

show abstract

A Non-local Approach to Shape from Ambient Shading

Cited by 10 publications

References 19 publications

Height from photometric ratio with model-based light source selection

Height from photometric ratio with model-based light source selection

Inverse Rendering of Faces with a 3D Morphable Model

Photometric Ambient Occlusion

Contact Info

Product

Resources

About