Name
Abstract | ||
|---|---|---|
Motion blur frequently occurs in dense 3D reconstruction using a single moving camera, and it degrades the quality of the 3D reconstruction. To handle motion blur caused by rapid camera shakes, we propose a blur-aware depth reconstruction method, which utilizes a pixel correspondence that is obtained by considering the effect of motion blur. Motion blur is dependent on 3D geometry, thus parameter zing blurred appearance of images with scene depth given camera motion is possible and a depth map can be accurately estimated from the blur-considered pixel correspondence. The estimated depth is then converted into pixel-wise blur kernels, and non-uniform motion blur is easily removed with low computational cost. The obtained blur kernel is depth-dependent, thus it effectively addresses scene-depth variation, which is a challenging problem in conventional non-uniform deblurring methods. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.42 | CVPR |
Keywords | Field | DocType |
depth map,scene-depth variation,dense 3d reconstruction,motion blur,estimated depth,single moving camera,pixel-wise blur kernel,scene depth,computational geometry,nonuniform deblurring method,estimation theory,image restoration,camera motion,rapid camera shakes,blur-considered pixel correspondence,image reconstruction,parameter zing blurred appearance,blur kernel,3d geometry,nonuniform motion blur,blur-aware depth reconstruction method,rapid camera,image deblurring,visual slam,blur-aware depth reconstruction,non-uniform motion blur,severely blurred images,image motion analysis,linear programming,estimation,geometry,kernel | Iterative reconstruction,Computer vision,Pattern recognition,Deblurring,Computer science,Motion blur,Pixel,Motion interpolation,Artificial intelligence,Image restoration,Depth map,3D reconstruction | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
13 | 0.59 | 21 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hee Seok Lee | 1 | 65 | 3.79 |
| Kyoung Mu Lee | 2 | 3228 | 153.84 |