File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: What is Learned in Deep Uncalibrated Photometric Stereo?
Title | What is Learned in Deep Uncalibrated Photometric Stereo? |
---|---|
Authors | |
Keywords | Uncalibrated photometric stereo generalized bas-relief ambiguity deep neural network |
Issue Date | 2020 |
Citation | The 16th European Conference on Computer Vision (ECCV), Online, 23-28 August 2020 How to Cite? |
Abstract | This paper targets at discovering what a deep uncalibrated photometric stereo network learns to resolve the problem’s inherent ambiguity, and designing an effective network architecture based on the new insight to improve the performance. The recently proposed deep uncalibrated photometric stereo method achieved promising results in estimating directional lightings. However, what specifically inside the network contributes to its success remains a mystery. In this paper, we analyze the features learned by this method and find that they strikingly resemble attached shadows, shadings, and specular highlights, which are known to provide useful clues in resolving the generalized bas-relief (GBR) ambiguity. Based on this insight, we propose a guided calibration network, named GCNet, that explicitly leverages object shape and shading information for improved lighting estimation. Experiments on synthetic and real datasets show that GCNet achieves improved results in lighting estimation for photometric stereo, which echoes the findings of our analysis. We further demonstrate that GCNet can be directly integrated with existing calibrated methods to achieve improved results on surface normal estimation. Our code and model can be found at https://guanyingc. github. io/UPS-GCNet. |
Description | ECCV 2020 take place virtually due to COVID-19 Poster Presentation - Paper ID: 2266 |
Persistent Identifier | http://hdl.handle.net/10722/284145 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, G | - |
dc.contributor.author | Waechter, M | - |
dc.contributor.author | Shi, B | - |
dc.contributor.author | Wong, KKY | - |
dc.contributor.author | Matsushita, Y | - |
dc.date.accessioned | 2020-07-20T05:56:27Z | - |
dc.date.available | 2020-07-20T05:56:27Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | The 16th European Conference on Computer Vision (ECCV), Online, 23-28 August 2020 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284145 | - |
dc.description | ECCV 2020 take place virtually due to COVID-19 | - |
dc.description | Poster Presentation - Paper ID: 2266 | - |
dc.description.abstract | This paper targets at discovering what a deep uncalibrated photometric stereo network learns to resolve the problem’s inherent ambiguity, and designing an effective network architecture based on the new insight to improve the performance. The recently proposed deep uncalibrated photometric stereo method achieved promising results in estimating directional lightings. However, what specifically inside the network contributes to its success remains a mystery. In this paper, we analyze the features learned by this method and find that they strikingly resemble attached shadows, shadings, and specular highlights, which are known to provide useful clues in resolving the generalized bas-relief (GBR) ambiguity. Based on this insight, we propose a guided calibration network, named GCNet, that explicitly leverages object shape and shading information for improved lighting estimation. Experiments on synthetic and real datasets show that GCNet achieves improved results in lighting estimation for photometric stereo, which echoes the findings of our analysis. We further demonstrate that GCNet can be directly integrated with existing calibrated methods to achieve improved results on surface normal estimation. Our code and model can be found at https://guanyingc. github. io/UPS-GCNet. | - |
dc.language | eng | - |
dc.relation.ispartof | European Conference on Computer Vision (ECCV) | - |
dc.subject | Uncalibrated photometric stereo | - |
dc.subject | generalized bas-relief ambiguity | - |
dc.subject | deep neural network | - |
dc.title | What is Learned in Deep Uncalibrated Photometric Stereo? | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wong, KKY: kykwong@cs.hku.hk | - |
dc.identifier.authority | Wong, KKY=rp01393 | - |
dc.identifier.hkuros | 310949 | - |