Skip to Main content Skip to Navigation
Conference papers

Efficient Dense Disparity Map Reconstruction using Sparse Measurements

Abstract : In this paper, we propose a new stereo matching algorithm able to reconstruct efficiently a dense disparity maps from few sparse disparity measurements. The algorithm is initialized by sampling the reference image using the Simple Linear Iterative Clustering (SLIC) superpixel method. Then, a sparse disparity map is generated only for the obtained boundary pixels. The reconstruction of the entire disparity map is obtained through the scanline propagation method. Outliers were effectively removed using an adaptive vertical median filter. Experimental results were conducted on the standard and the new Middlebury datasets show that the proposed method produces high-quality dense disparity results.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download
Contributor : Cédric Demonceaux <>
Submitted on : Tuesday, March 6, 2018 - 6:10:14 PM
Last modification on : Monday, March 30, 2020 - 8:41:53 AM
Document(s) archivé(s) le : Thursday, June 7, 2018 - 2:40:35 PM


Files produced by the author(s)


  • HAL Id : hal-01724779, version 1


Oussama Zeglazi, Mohammed Rziza, Aouatif Amine, Cédric Demonceaux. Efficient Dense Disparity Map Reconstruction using Sparse Measurements. 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2018), Jan 2018, Madère, Portugal. ⟨hal-01724779⟩



Record views


Files downloads