Image-Based Rendering for Large-Scale Outdoor Scenes With Fusion of Monocular and Multi-View Stereo Depth

IEEE Access

Tianlu Mao¹  Zhaoxin Li¹  Shuang Liu²  Xiaona Zhang²  Jing Liu²  Minghao Li³  Shaohua Liu³ 

[1] Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;College of Computer and Cyber Security, Hebei Normal University, Shijiazhuang, China;School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China;

关键词: Image-based rendering;    multi-view stereo;    monocular depth estimation;    view synthesis;    outdoor scenes;   

DOI  :  10.1109/ACCESS.2020.3004431

来源: DOAJ

【 摘 要 】

Image-based rendering (IBR) attempts to synthesize novel views using a set of observed images. Some IBR approaches (such as light fields) have yielded impressive high-quality results on small-scale scenes with dense photo capture. However, available wide-baseline IBR methods are still restricted by the low geometric accuracy and completeness of multi-view stereo (MVS) reconstruction on low-textured and non-Lambertian surfaces. The issues become more significant in large-scale outdoor scenes due to challenging scene content, e.g., buildings, trees, and sky. To address these problems, we present a novel IBR algorithm that consists of two key components. First, we propose a novel depth refinement method that combines MVS depth maps with monocular depth maps predicted via deep learning. A lookup table remap is proposed for converting the scale of the monocular depths to be consistent with the scale of the MVS depths. Then, the rescaled monocular depth is used as the constraint in the minimum spanning tree (MST)-based nonlocal filter to refine the per-view MVS depth. Second, we present an efficient shape-preserving warping algorithm that uses superpixels to generate the warped images and blend expected novel views of scenes. The proposed method has been evaluated on public MVS and view synthesis datasets, as well as newly captured large-scale outdoor datasets. In comparison with state-of-the-art methods, the experimental results demonstrated that the proposed method can obtain more complete and reliable depth maps for the challenging large-scale outdoor scenes, thereby resulting in more promising novel view synthesis.

【 授权许可】

Unknown