Dense multiview stereo based on image texture enhancement. (26th November 2020)

• Record Type: Journal Article
• Authors: Liao, Jie; Wei, Mengqiang; Fu, Yanping; Yan, Qingan; Xiao, Chunxia
• Is Part Of: Computer animation and virtual worlds. Volume 32:Number 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-11-26
• Subjects: 3D reconstruction -- multiview stereo -- texture enhancement; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.1979
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: In this paper, we propose a novel Multiview Stereo (MVS) method which can effectively estimate geometry in low‐textured regions. Conventional MVS algorithms predict geometry by performing dense correspondence estimation across multiple views under the constraint of epipolar geometry. As low‐textured regions contain less feature information for reliable matching, estimating geometry for low‐textured regions remains hard work for previous MVS methods. To address this issue, we propose an MVS method based on texture enhancement. By enhancing texture information for each input image via our multiscale bilateral decomposition and reconstruction algorithm, our method can estimate reliable geometry for low‐textured regions that are intractable for previous MVS methods. To densify the final output point cloud, we further propose a novel selective joint bilateral propagation filter, which can effectively propagate reliable geometry estimation to neighboring unpredicted regions. We validate the effectiveness of our method on the ETH3D benchmark. Quantitative and qualitative comparisons demonstrate that our method can significantly improve the quality of reconstruction in low‐textured regions. Abstract : In this paper, we propose a novel multiview stereo (MVS) method which can effectively estimate geometry in low‐textured regions. By enhancing texture information for each input image via multiscale bilateral decomposition and reconstruction, our method can perform reliable geometry estimation for low‐textured regions. To further densify the depth and normal maps, we propose a novel selective joint bilateral propagation filter, which can effectively propagate reliable geometry estimation to neighboring unpredicted regions.