HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://guanyingc.github.io/SDPS-Net/
x-github-request-id: E088:21D6A4:9287B1:A43373:6952ABBD
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:26:38 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210067-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767025598.156500,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: 567c4c7b70e0b5efa631a5542753aebb1bf01d2d
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 24 Mar 2024 03:26:31 GMT
access-control-allow-origin: *
etag: W/"65ff9d67-4880"
expires: Mon, 29 Dec 2025 16:36:38 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 7EDA:1F53DD:91103D:A2BCD2:6952ABBD
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:26:38 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210067-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767025598.379001,VS0,VE219
vary: Accept-Encoding
x-fastly-request-id: 94a367233777edb02457878bcfd1f10580da4609
content-length: 3850
Self-calibrating Deep Photometric Stereo Networks
Self-calibrating Deep Photometric Stereo Networks
1The University of Hong Kong 2University of Oxford
3Peking University 4Peng Cheng Laboratory 5Osaka University
|
|
Abstract
This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning. Unlike previous approaches that heavily rely on assumptions of specific reflectances and light source distributions, our method is able to determine both shape and light directions of a scene with unknown arbitrary reflectances observed under unknown varying light directions. To achieve this goal, we propose a two-stage deep learning architecture, called SDPS-Net, which can effectively take advantage of intermediate supervision, resulting in reduced learning difficulty compared to a single-stage model. Experiments on both synthetic and real datasets show that our proposed approach significantly outperforms previous uncalibrated photometric stereo methods.
Method
|
|
The network architecture of SDPS-Net is composed of (a) Lighting Calibration Network and (b) Normal Estimation Network. Kernel sizes for all convolutional layers are 3 × 3, and values above the layers indicate the number of feature channels.
|
Training Dataset
|
|
We adopted the publicly available synthetic PS Blobby and Sculpture datasets for training. Blobby and Sculpture datasets provide surfaces with complex normal distributions and diverse materials from MERL dataset. Effects of cast shadow and inter-reflection were considered during rendering using the physically based raytracer Mitsuba. There are 85,212 samples in total. Each sample was rendered under 64 distinct light directions sampled from the upper-hemisphere with uniform light intensity, resulting in 5,453,568 images (85,212 X 64). The rendered images have a dimension of 128 X 128.
|
Results on Real Dataset
1. DiLiGenT Main Dataset.
|
Up to Down: Sample Input, Object, GT Normal, Results of SDPS-Net, and Error Map
|
|
|
|
|
2. Light Stage Data Gallery.
Up to Down: Sample Input, Object, Results of SDPS-Net and UPS-FCN
|
|
|
|
Code and Model
Code, models and datasets are available at Github!
Acknowledgments
We thank the anonymous reviewers for their constructive comments. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU. Kai Han is supported by EPSRC Programme Grant Seebibyte EP/M013774/1. Boxin Shi is supported in part by National Science Foundation of China under Grant No. 61872012. Yasuyuki Matsushita is supported by the New Energy and Industrial Technology Development Organization (NEDO).
|
Webpage template borrowed from Split-Brain Autoencoders, CVPR 2017.
