期刊
INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 130, 期 12, 页码 3014-3034出版社
SPRINGER
DOI: 10.1007/s11263-022-01684-8
关键词
Photometric stereo; High-frequency surface normals; Non-Lambertian; Deep neural network
资金
- Key-Area Research and Development Program of Guangdong Province [2020B090928001]
- Project of Strategic Importance Fund from The Hong Kong Polytechnic University [ZE1X]
- National Key R&D Program of China [2018AAA0100602]
- National Key Scientific Instrument and Equipment Development Projects of China [41927805]
- National Natural Science Foundation of China [61872012, 62136001, 61976123, 61601427]
- Key Development Program for Basic Research of Shandong Province [ZR2020ZD44]
- Taishan Young Scholars Program of Shandong Province
This paper proposes a normalized attention-weighted photometric stereo network (NormAttention-PSN) to improve the ability to handle high-frequency surface regions. Extensive experiments on public benchmark data sets show that the proposed method outperforms traditional methods and state-of-the-art deep learning-based methods.
Photometric stereo aims to recover the surface normals of a 3D object from various shading cues, establishing the relationship between two-dimensional images and the object geometry. Traditional methods usually adopt simplified reflectance models to approximate the non-Lambertian surface properties, while recently, photometric stereo based on deep learning has been widely used to deal with non-Lambertian surfaces. However, previous studies are limited in dealing with high-frequency surface regions, i.e., regions with rapid shape variations, such as crinkles, edges, etc., resulted in blurry reconstructions. To alleviate this problem, we present a normalized attention-weighted photometric stereo network, namely NormAttention-PSN, to improve surface orientation prediction, especially for those complicated structures. In order to address these challenges, in this paper, we (1) present an attention-weighted loss to produce better surface reconstructions, which applies a higher weight to the detail-preserving gradient loss in high-frequency areas, (2) adopt a double-gate normalization method for non-Lambertian surfaces, to explicitly distinguish whether the high-frequency representation is stimulated by surface structure or spatially varying reflectance, and (3) adopt a parallel high-resolution structure to generate deep features that can maintain the high-resolution details of surface normals. Extensive experiments on public benchmark data sets show that the proposed NormAttention-PSN significantly outperforms traditional calibrated photometric stereo algorithms and state-of-the-art deep learning-based methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据