Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

被引:116
作者
Li, Zhengqin [1 ]
Sunkavalli, Kalyan [2 ]
Chandraker, Manmohan [1 ]
机构
[1] Univ Calif San Diego, San Diego, CA 92103 USA
[2] Adobe Res, San Jose, CA USA
来源
COMPUTER VISION - ECCV 2018, PT III | 2018年 / 11207卷
基金
美国国家科学基金会;
关键词
REFLECTANCE;
D O I
10.1007/978-3-030-01219-9_5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera. Our method images the surface under arbitrary environment lighting with the flash turned on, thereby avoiding shadows while simultaneously capturing high-frequency specular highlights. We train a CNN to regress an SVBRDF and surface normals from this image. Our network is trained using a large-scale SVBRDF dataset and designed to incorporate physical insights for material estimation, including an in-network rendering layer to model appearance and a material classifier to provide additional supervision during training. We refine the results from the network using a dense CRF module whose terms are designed specifically for our task. The framework is trained end-to-end and produces high quality results for a variety of materials. We provide extensive ablation studies to evaluate our network on both synthetic and real data, while demonstrating significant improvements in comparisons with prior works.
引用
收藏
页码:74 / 90
页数:17
相关论文
共 37 条
[1]   Reflectance Modeling by Neural Texture Synthesis [J].
Aittala, Miika ;
Aila, Timo ;
Lehtinen, Jaakko .
ACM TRANSACTIONS ON GRAPHICS, 2016, 35 (04)
[2]   Two-Shot SVBRDF Capture for Stationary Materials [J].
Aittala, Miika ;
Weyrich, Tim ;
Lehtinen, Jaakko .
ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04)
[3]  
[Anonymous], ARXIV161208510
[4]  
[Anonymous], 2013, AAAI
[5]  
[Anonymous], 2015, P IEEE INT C COMP VI
[6]  
[Anonymous], 2017, ARXIV170402157
[7]  
[Anonymous], 2017, ACM Trans. Graph.
[8]  
Bell Sean, 2015, COMPUTER VISION PATT
[9]  
BLINN JF, 1976, COMMUN ACM, V19, P542, DOI 10.1145/965143.563322
[10]   The Information Available to a Moving Observer on Shape with Unknown, Isotropic BRDFs [J].
Chandraker, Manmohan .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (07) :1283-1297