On Three-Dimensional Surface Reconstruction Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
Surface Shape Reconstruction of a Nonrigid Transport Object Using Refraction and Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer graphics (2nd ed.): C version
Computer graphics (2nd ed.): C version
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Environment matting and compositing
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Environment matting extensions: towards higher accuracy and real-time capture
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Acquisition and rendering of transparent and refractive objects
EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Image-based environment matting
EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Conveying the 3D Shape of Smoothly Curving Transparent Surfaces via Texture
IEEE Transactions on Visualization and Computer Graphics
Ray Tracing with Polarization Parameters
IEEE Computer Graphics and Applications
On different facets of regularization theory
Neural Computation
Polarization-based Transparent Surface Modeling from Two Views
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A neural network for recovering 3D shape from erroneous and few depth maps of shaded images
Pattern Recognition Letters
A combinatorial transparent surface modeling from polarization images
IWCIA'04 Proceedings of the 10th international conference on Combinatorial Image Analysis
Multiple-view shape extraction from shading as local regression by analytic NN scheme
Mathematical and Computer Modelling: An International Journal
| Hi-index | 0.00 |
This paper presents a neural network (NN) to recover three-dimensional (3D) shape of an object from its multiple view images. The object may contain non-overlapping transparent and opaque surfaces. The challenge is to simultaneously reconstruct the transparent and opaque surfaces given only a limited number of views. By minimizing the pixel error between the output images of this NN and teacher images, we want to refine vertices position of an initial 3D polyhedron model to approximate the true shape of the object. For that purpose, we incorporate a ray tracing formulation into our NN’s mapping and learning. At the implementation stage, we develop a practical regularization learning method using texture mapping instead of ray tracing. By choosing an appropriate regularization parameter and optimizing using hierarchical learning and annealing strategies, our NN gives more approximate shape.