File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-01240-3_1
- Scopus: eid_2-s2.0-85055083702
- WOS: WOS:000594233000001
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: PS-FCN: A Flexible Learning Framework for Photometric Stereo
Title | PS-FCN: A Flexible Learning Framework for Photometric Stereo |
---|---|
Authors | |
Keywords | Photometric stereo Convolutional neural network |
Issue Date | 2018 |
Publisher | Springer. |
Citation | European Conference on Computer Vision (ECCV), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII, p. 3-19 How to Cite? |
Abstract | This paper addresses the problem of photometric stereo for non-Lambertian surfaces. Existing approaches often adopt simplified reflectance models to make the problem more tractable, but this greatly hinders their applications on real-world objects. In this paper, we propose a deep fully convolutional network, called PS-FCN, that takes an arbitrary number of images of a static object captured under different light directions with a fixed camera as input, and predicts a normal map of the object in a fast feed-forward pass. Unlike the recently proposed learning based method, PS-FCN does not require a pre-defined set of light directions during training and testing, and can handle multiple images and light directions in an order-agnostic manner. Although we train PS-FCN on synthetic data, it can generalize well on real datasets. We further show that PS-FCN can be easily extended to handle the problem of uncalibrated photometric stereo. Extensive experiments on public real datasets show that PS-FCN outperforms existing approaches in calibrated photometric stereo, and promising results are achieved in uncalibrated scenario, clearly demonstrating its effectiveness. |
Description | Poster session 3A - no. P-3A-34 |
Persistent Identifier | http://hdl.handle.net/10722/261167 |
ISBN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, G | - |
dc.contributor.author | Han, K | - |
dc.contributor.author | Wong, KKY | - |
dc.date.accessioned | 2018-09-14T08:53:35Z | - |
dc.date.available | 2018-09-14T08:53:35Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | European Conference on Computer Vision (ECCV), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII, p. 3-19 | - |
dc.identifier.isbn | 9783030012601 | - |
dc.identifier.uri | http://hdl.handle.net/10722/261167 | - |
dc.description | Poster session 3A - no. P-3A-34 | - |
dc.description.abstract | This paper addresses the problem of photometric stereo for non-Lambertian surfaces. Existing approaches often adopt simplified reflectance models to make the problem more tractable, but this greatly hinders their applications on real-world objects. In this paper, we propose a deep fully convolutional network, called PS-FCN, that takes an arbitrary number of images of a static object captured under different light directions with a fixed camera as input, and predicts a normal map of the object in a fast feed-forward pass. Unlike the recently proposed learning based method, PS-FCN does not require a pre-defined set of light directions during training and testing, and can handle multiple images and light directions in an order-agnostic manner. Although we train PS-FCN on synthetic data, it can generalize well on real datasets. We further show that PS-FCN can be easily extended to handle the problem of uncalibrated photometric stereo. Extensive experiments on public real datasets show that PS-FCN outperforms existing approaches in calibrated photometric stereo, and promising results are achieved in uncalibrated scenario, clearly demonstrating its effectiveness. | - |
dc.language | eng | - |
dc.publisher | Springer. | - |
dc.relation.ispartof | European Conference on Computer Vision (ECCV) | - |
dc.rights | The version of record of this paper is available online at Publisher’s website: https://doi.org/10.1007/978-3-030-01240-3_1 | - |
dc.subject | Photometric stereo | - |
dc.subject | Convolutional neural network | - |
dc.title | PS-FCN: A Flexible Learning Framework for Photometric Stereo | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wong, KKY: kykwong@cs.hku.hk | - |
dc.identifier.authority | Wong, KKY=rp01393 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1007/978-3-030-01240-3_1 | - |
dc.identifier.scopus | eid_2-s2.0-85055083702 | - |
dc.identifier.hkuros | 290259 | - |
dc.identifier.spage | 3 | - |
dc.identifier.epage | 19 | - |
dc.identifier.isi | WOS:000594233000001 | - |
dc.publisher.place | Cham, Switzerland | - |