A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape from shading
Uniqueness in shape from shading
International Journal of Computer Vision
Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
The digital Michelangelo project: 3D scanning of large statues
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Fast texture synthesis using tree-structured vector quantization
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Image quilting for texture synthesis and transfer
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Limits on Super-Resolution and How to Break Them
IEEE Transactions on Pattern Analysis and Machine Intelligence
Reliable Surface Reconstructiuon from Multiple Range Images
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Surface Modeling and Display from Range and Color Data
ICIAP '97 Proceedings of the 9th International Conference on Image Analysis and Processing-Volume I - Volume I
Range Synthesis for 3D Environment Modeling
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Texture Synthesis by Non-Parametric Sampling
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
| Hi-index | 0.00 |
This paper developed prior work which incrementallycompletes a sparse depth map based on inter-image statisticsinformation. In that prior work, we have observed thatpixel ordering of the incremental recovery is critical to thequality of the final results. In this paper we demonstrate improvedperformance using an information-driven recoverypolicy to determine this ordering. We have also observedthat the reconstruction across depth discontinuities was oftenproblematic as there was comparatively little constraintfor probabilistic inference at those locations. Further, suchlocations are often identified with edges in both the rangeand intensity maps. We address this problem by deferringthe reconstruction of voxels close to intensity or depth discontinuities,leading to improved results. We also show thatcolor information can improve reconstruction quality. Experimentalresults are presented to demonstrate the qualityof the recover and to illustrate some new application domainssuch as deblurring and underwater scattering compensation.