Shape from Defocus via Diffusion

Authors:
Paolo Favaro;Stefano Soatto;Martin Burger;Stanley J. Osher
Affiliations:
-;-;-;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2008

Citing 0
Cited 10

Discontinuity-Adaptive Shape from Focus Using a Non-convex Prior

Proceedings of the 31st DAGM Symposium on Pattern Recognition
Real Aperture Axial Stereo: Solving for Correspondences in Blur

Proceedings of the 31st DAGM Symposium on Pattern Recognition
A novel iterative shape from focus algorithm based on combinatorial optimization

Pattern Recognition
Defocus map estimation from a single image

Pattern Recognition
Towards Unrestrained Depth Inference with Coherent Occlusion Filling

International Journal of Computer Vision
3D Imaging for hand gesture recognition: Exploring the software-hardware interaction of current technologies

3D Research
Iterative feedback estimation of depth and radiance from defocused images

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Recovering Relative Depth from Low-Level Features Without Explicit T-junction Detection and Interpretation

International Journal of Computer Vision
Single-lens low-disparity stereo using microlenses

Journal of Systems Architecture: the EUROMICRO Journal
Shape from Sharp and Motion-Blurred Image Pair

International Journal of Computer Vision

Quantified Score

Hi-index	0.14

Visualization

Abstract

Defocus can be modeled as a diffusion process and represented mathematically using the heat equation, where image blur corresponds to the diffusion of heat. This analogy can be extended to non-planar scenes by allowing a space-varying diffusion coefficient. The inverse problem of reconstructing 3-D structure from blurred images corresponds to an “inverse diffusion” that is notoriously ill-posed. We show how to bypass this problem by using the notion of relative blur. Given two images, within each neighborhood, the amount of diffusion necessary to transform the sharper image into the blurrier one depends on the depth of the scene. This can be used to devise a global algorithm to estimate the depth profile of the scene without recovering the deblurred image, using only forward diffusion.