The variational approach to shape from shading
Computer Vision, Graphics, and Image Processing
Shape from shading
A viscosity solutions approach to shape-from-shading
SIAM Journal on Numerical Analysis
Measuring and modeling anisotropic reflection
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
Shape from shading with perspective projection
CVGIP: Image Understanding
Shape from shading with a generalized reflectance map model
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIAM Review
Illumination for computer generated pictures
Communications of the ACM
Models of light reflection for computer synthesized pictures
SIGGRAPH '77 Proceedings of the 4th annual conference on Computer graphics and interactive techniques
Optimal Algorithm for Shape from Shading and Path Planning
Journal of Mathematical Imaging and Vision
Shape-from-Shading Under Perspective Projection
International Journal of Computer Vision
A Generic and Provably Convergent Shape-from-Shading Method for Orthographic and Pinhole Cameras
International Journal of Computer Vision
High Order Fast Sweeping Methods for Static Hamilton---Jacobi Equations
Journal of Scientific Computing
Numerical methods for shape-from-shading: A new survey with benchmarks
Computer Vision and Image Understanding
A Novel Shape from Shading Algorithm for Non-Lambertian Surfaces
ICMTMA '11 Proceedings of the 2011 Third International Conference on Measuring Technology and Mechatronics Automation - Volume 01
Hi-index | 0.00 |
Shape recovery is a basic problem in computer vision. Shape from shading (SFS) is an approach to get the 3D shape from a single shading image. Diffuse model is usually used to approximate the surface reflectance property. For specular surfaces, however, it is not suitable. In this paper, we propose a new SFS approach for specular surfaces. The Blinn-Phong reflectance model is applied to characterize the specular reflection property. The image irradiance equation for specular surfaces is obtained under the assumptions that the camera performs an orthographic projection and its direction is the same as the light source. Then, it is formulated as an Eikonal PDE which includes the shape of the surfaces. The viscosity solution of the resulting PDE is approximated by using the high-order Godunov fast sweeping method. Experiments are performed on both sphere and vase images and the results show the efficiency of the proposed approach.