Fast and Accurate Depth Estimation From Sparse Light Fields
| Autor: | Aleksandra Chuchvara, Attila Barsi, Atanas Gotchev |
|---|---|
| Přispěvatelé: | Tampere University, Computing Sciences, Research group: 3D MEDIA, Doctoral Programme in Computing and Electrical Engineering |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Graphics hardware 3D reconstruction Image and Video Processing (eess.IV) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Electrical Engineering and Systems Science - Image and Video Processing 113 Computer and information sciences Computer Graphics and Computer-Aided Design Stability (probability) Reduction (complexity) Depth map Computer Science::Computer Vision and Pattern Recognition 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Software Light field |
| Popis: | We present a fast and accurate method for dense depth reconstruction from sparsely sampled light fields obtained using a synchronized camera array. In our method, the source images are over-segmented into non-overlapping compact superpixels that are used as basic data units for depth estimation and refinement. Superpixel representation provides a desirable reduction in the computational cost while preserving the image geometry with respect to the object contours. Each superpixel is modeled as a plane in the image space, allowing depth values to vary smoothly within the superpixel area. Initial depth maps, which are obtained by plane sweeping, are iteratively refined by propagating good correspondences within an image. To ensure the fast convergence of the iterative optimization process, we employ a highly parallel propagation scheme that operates on all the superpixels of all the images at once, making full use of the parallel graphics hardware. A few optimization iterations of the energy function incorporating superpixel-wise smoothness and geometric consistency constraints allows to recover depth with high accuracy in textured and textureless regions as well as areas with occlusions, producing dense globally consistent depth maps. We demonstrate that while the depth reconstruction takes about a second per full high-definition view, the accuracy of the obtained depth maps is comparable with the state-of-the-art results. Comment: 15 pages, 15 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|