Item type |
SIG Technical Reports(1) |
公開日 |
2025-01-14 |
タイトル |
|
|
タイトル |
Neural SDF for Shadow-aware Unsupervised Structured Light |
タイトル |
|
|
言語 |
en |
|
タイトル |
Neural SDF for Shadow-aware Unsupervised Structured Light |
言語 |
|
|
言語 |
eng |
資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
著者所属 |
|
|
|
Kyushu University |
著者所属 |
|
|
|
Kyushu University |
著者所属 |
|
|
|
Kyushu University |
著者所属 |
|
|
|
Kyushu University |
著者所属(英) |
|
|
|
en |
|
|
Kyushu University |
著者所属(英) |
|
|
|
en |
|
|
Kyushu University |
著者所属(英) |
|
|
|
en |
|
|
Kyushu University |
著者所属(英) |
|
|
|
en |
|
|
Kyushu University |
著者名 |
Kazuto, Ichimaru
Diego, Thomas
Takafumi, Iwaguchi
Hiroshi, Kawasaki
|
著者名(英) |
Kazuto, Ichimaru
Diego, Thomas
Takafumi, Iwaguchi
Hiroshi, Kawasaki
|
論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Among various active 3D measurement techniques, Structured Light (SL) is one of the most popular methods for its robustness and high accuracy. The ordinary SL system consists of a camera and a projector, and by projecting a pre-defined pattern, we can obtain pixel-to-pixel correspondences between the camera and the projector for triangulation. However, if we lack knowledge of the projected pattern for some reason, e.glet@tokeneonedot, the projected pattern is not as expected due to lens distortion, inaccurate calibration, undesired optical phenomena like inter-reflection, and so on, the accuracy of conventional SL is severely degraded. As a remedy, we propose unsupervised structured light (USSL), which does not explicitly use prior knowledge of the pattern. Inspired by the fact that humans can recognize the scene structure illuminated by an unknown light source (e.glet@tokeneonedot. rotating mirror ball), and some prior works have succeeded in novel-view-synthesis under unknown illumination conditions, we implement USSL on Neural Signed Distance Fields (Neural SDF) pipeline with implicit reflection module powered by a neural network. Additionally, since every SL method causes occlusion (shadow) by pattern projection, we must consider it for accurate shape reconstruction. To this end, we integrate shadow volume rendering into the proposed pipeline. Experiments with synthetic and real datasets are conducted to confirm the feasibility of the proposed method. |
論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Among various active 3D measurement techniques, Structured Light (SL) is one of the most popular methods for its robustness and high accuracy. The ordinary SL system consists of a camera and a projector, and by projecting a pre-defined pattern, we can obtain pixel-to-pixel correspondences between the camera and the projector for triangulation. However, if we lack knowledge of the projected pattern for some reason, e.glet@tokeneonedot, the projected pattern is not as expected due to lens distortion, inaccurate calibration, undesired optical phenomena like inter-reflection, and so on, the accuracy of conventional SL is severely degraded. As a remedy, we propose unsupervised structured light (USSL), which does not explicitly use prior knowledge of the pattern. Inspired by the fact that humans can recognize the scene structure illuminated by an unknown light source (e.glet@tokeneonedot. rotating mirror ball), and some prior works have succeeded in novel-view-synthesis under unknown illumination conditions, we implement USSL on Neural Signed Distance Fields (Neural SDF) pipeline with implicit reflection module powered by a neural network. Additionally, since every SL method causes occlusion (shadow) by pattern projection, we must consider it for accurate shape reconstruction. To this end, we integrate shadow volume rendering into the proposed pipeline. Experiments with synthetic and real datasets are conducted to confirm the feasibility of the proposed method. |
書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11131797 |
書誌情報 |
研究報告コンピュータビジョンとイメージメディア(CVIM)
巻 2025-CVIM-240,
号 33,
p. 1-8,
発行日 2025-01-14
|
ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8701 |
Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |