File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2019.00112
- Scopus: eid_2-s2.0-85076707471
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Single-image piece-wise planar 3D reconstruction via associative embedding
Title | Single-image piece-wise planar 3D reconstruction via associative embedding |
---|---|
Authors | |
Keywords | 3D from Single Image Grouping and Shape Segmentation |
Issue Date | 2019 |
Citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, v. 2019-June, p. 1029-1037 How to Cite? |
Abstract | Single-image piece-wise planar 3D reconstruction aims to simultaneously segment plane instances and recover 3D plane parameters from an image. Most recent approaches leverage convolutional neural networks (CNNs) and achieve promising results. However, these methods are limited to detecting a fixed number of planes with certain learned order. To tackle this problem, we propose a novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation. In the first stage, we train a CNN to map each pixel to an embedding space where pixels from the same plane instance have similar embeddings. Then, the plane instances are obtained by grouping the embedding vectors in planar regions via an efficient mean shift clustering algorithm. In the second stage, we estimate the parameter for each plane instance by considering both pixel-level and instance-level consistencies. With the proposed method, we are able to detect an arbitrary number of planes. Extensive experiments on public datasets validate the effectiveness and efficiency of our method. Furthermore, our method runs at 30 fps at the testing time, thus could facilitate many real-time applications such as visual SLAM and human-robot interaction. Code is available at https://github.com/svip-lab/PlanarReconstruction. |
Persistent Identifier | http://hdl.handle.net/10722/344999 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yu, Zehao | - |
dc.contributor.author | Zheng, Jia | - |
dc.contributor.author | Lian, Dongze | - |
dc.contributor.author | Zhou, Zihan | - |
dc.contributor.author | Gao, Shenghua | - |
dc.date.accessioned | 2024-08-15T09:24:35Z | - |
dc.date.available | 2024-08-15T09:24:35Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, v. 2019-June, p. 1029-1037 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/344999 | - |
dc.description.abstract | Single-image piece-wise planar 3D reconstruction aims to simultaneously segment plane instances and recover 3D plane parameters from an image. Most recent approaches leverage convolutional neural networks (CNNs) and achieve promising results. However, these methods are limited to detecting a fixed number of planes with certain learned order. To tackle this problem, we propose a novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation. In the first stage, we train a CNN to map each pixel to an embedding space where pixels from the same plane instance have similar embeddings. Then, the plane instances are obtained by grouping the embedding vectors in planar regions via an efficient mean shift clustering algorithm. In the second stage, we estimate the parameter for each plane instance by considering both pixel-level and instance-level consistencies. With the proposed method, we are able to detect an arbitrary number of planes. Extensive experiments on public datasets validate the effectiveness and efficiency of our method. Furthermore, our method runs at 30 fps at the testing time, thus could facilitate many real-time applications such as visual SLAM and human-robot interaction. Code is available at https://github.com/svip-lab/PlanarReconstruction. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.subject | 3D from Single Image | - |
dc.subject | Grouping and Shape | - |
dc.subject | Segmentation | - |
dc.title | Single-image piece-wise planar 3D reconstruction via associative embedding | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2019.00112 | - |
dc.identifier.scopus | eid_2-s2.0-85076707471 | - |
dc.identifier.volume | 2019-June | - |
dc.identifier.spage | 1029 | - |
dc.identifier.epage | 1037 | - |