PolyRoom: Room-Aware Transformer for Floorplan Reconstruction
Pages 322 - 339
Abstract
Reconstructing geometry and topology structures from raw unstructured data has always been an important research topic in indoor mapping research. In this paper, we aim to reconstruct the floorplan with a vectorized representation from point clouds. Despite significant advancements achieved in recent years, current methods still encounter several challenges, such as missing corners or edges, inaccuracies in corner positions or angles, self-intersecting or overlapping polygons, and potentially implausible topology. To tackle these challenges, we present PolyRoom, a room-aware Transformer that leverages uniform sampling representation, room-aware query initialization, and room-aware self-attention for floorplan reconstruction. Specifically, we adopt a uniform sampling floorplan representation to enable dense supervision during training and effective utilization of angle information. Additionally, we propose a room-aware query initialization scheme to prevent non-polygonal sequences and introduce room-aware self-attention to enhance memory efficiency and model performance. Experimental results on two widely used datasets demonstrate that PolyRoom surpasses current state-of-the-art methods both quantitatively and qualitatively. Our code is available at: https://github.com/3dv-casia/PolyRoom/.
References
[1]
Avetisyan, A., Khanova, T., Choy, C., Dash, D., Dai, A., Nießner, M.: SceneCAD: predicting object alignments and layouts in RGB-D scans. In: European Conference on Computer Vision (ECCV), pp. 596–612 (2020)
[2]
Browne, C.B., et al.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1–43 (2012)
[3]
Cabral, R., Furukawa, Y.: Piecewise planar and compact floorplan reconstruction from images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 628–635 (2014)
[4]
Castrejon, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a polygon-RNN. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4485–4493 (2017)
[5]
Chen, C., Wang, R., Vogel, C., Pollefeys, M.: F3Loc: fusion and filtering for floorplan localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18029–18038 (2024)
[6]
Chen, J., Deng, R., Furukawa, Y.: PolyDiffuse: polygonal shape reconstruction via guided set diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1863–1888 (2023)
[7]
Chen, J., Liu, C., Wu, J., Furukawa, Y.: Floor-SP: inverse CAD for floorplans by sequential room-wise shortest path. In: IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2661–2670 (2019)
[8]
Chen, J., Qian, Y., Furukawa, Y.: HEAT: holistic edge attention Transformer for structured reconstruction. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3856–3865 (2022)
[9]
Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask Transformer for universal image segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1280–1289 (2022)
[10]
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432–2443 (2017)
[11]
Dosovitskiy, A., et al.: An image is worth 1616 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2020)
[12]
Douglas DH and Peucker TK Algorithms for the reduction of the number of points required to represent a digitized line or its caricature Cartographica 1973 10 2 112-122
[13]
Fan, Z., Zhu, L., Li, H., Chen, X., Zhu, S., Tan, P.: FloorPlanCAD: a large-scale CAD drawing dataset for panoptic symbol spotting. In: IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10108–10117 (2021)
[14]
Favreau JD, Lafarge F, Bousseau A, and Auvolat A Extracting geometric structures in images with Delaunay point processes IEEE Trans. Pattern Anal. Mach. Intell. 2019 42 4 837-850
[15]
Han J, Liu Y, Rong M, Zheng X, and Shen S FloorUSG: indoor floorplan reconstruction by unifying 2D semantics and 3D geometry ISPRS J. Photogramm. Remote. Sens. 2023 196 490-501
[16]
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
[17]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
[18]
Hochreiter S and Schmidhuber J Long short-term memory Neural Comput. 1997 9 8 1735-1780
[19]
Hu Y, Wang Z, Huang Z, and Liu Y PolyBuilding: polygon transformer for building extraction ISPRS J. Photogramm. Remote. Sens. 2023 199 15-27
[20]
Ibrahem, H., Salem, A., Kang, H.S.: ST-RoomNet: learning room layout estimation from single image through unsupervised spatial transformations. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3376–3384 (2023)
[21]
Ikehata, S., Yang, H., Furukawa, Y.: Structured indoor modeling. In: IEEE International Conference on Computer Vision (ICCV), pp. 1323–1331 (2015)
[22]
Jiang, Z., Xiang, Z., Xu, J., Zhao, M.: LGT-Net: indoor panoramic room layout estimation with geometry-aware transformer network. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1644–1653 (2022)
[23]
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)
[24]
Lazarow, J., Xu, W., Tu, Z.: Instance segmentation with mask-supervised polygonal boundary Transformers. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4372–4381 (2022)
[25]
Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., Rabinovich, A.: RoomNet: end-to-end room layout estimation. In: IEEE International Conference on Computer Vision (ICCV), pp. 4875–4884 (2017)
[26]
Li, J., Chan, C.L., Le Chan, J., Li, Z., Wan, K.W., Yau, W.Y.: Cognitive navigation for indoor environment using floorplan. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9030–9037. IEEE (2021)
[27]
Liang, J., Homayounfar, N., Ma, W.C., Xiong, Y., Hu, R., Urtasun, R.: PolyTransform: deep polygon transformer for instance segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9128–9137 (2020)
[28]
Liao, B., et al.: MapTRv2: an end-to-end framework for online vectorized HD map construction. arXiv preprint arXiv:2308.05736 (2023)
[29]
Liu, H., et al.: Lightweight structured line map based visual localization. IEEE Robot. Automat. Lett. 9(6), 5182–5189 (2024)
[30]
Liu, J., et al.: PolyFormer: referring image segmentation as sequential polygon generation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18653–18663 (2023)
[31]
Liu, Z., et al.: Swin transformer: hierarchical vision Transformer using shifted windows. In: IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9992–10002 (2021)
[32]
Peng, S., Jiang, W., Pi, H., Li, X., Bao, H., Zhou, X.: Deep snake for real-time instance segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8530–8539 (2020)
[33]
Stekovic, S., Rad, M., Fraundorfer, F., Lepetit, V.: MonteFloor: extending MCTs for reconstructing accurate large-scale floor plans. In: IEEE/CVF International Conference on Computer Vision (ICCV), pp. 16014–16023 (2021)
[34]
Su, J.W., Tung, K.Y., Peng, C.H., Wonka, P., Chu, H.K.: SLIBO-Net: floorplan reconstruction via slicing box representation with local geometry regularization. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 48781–48792 (2023)
[35]
Sun, C., Hsiao, C.W., Sun, M., Chen, H.T.: HorizonNet: learning room layout with 1D representation and pano stretch data augmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1047–1056 (2019)
[36]
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS) (2017)
[37]
Xu, Y., Xu, W., Cheung, D., Tu, Z.: Line segment detection using transformers without edges. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4255–4264 (2021)
[38]
Xue, N., et al.: Holistically-attracted wireframe parsing. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2785–2794 (2020)
[39]
Yue, Y., Kontogianni, T., Schindler, K., Engelmann, F.: Connecting the dots: floorplan reconstruction using two-level queries. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 845–854 (2023)
[40]
Zhang, F., Xu, X., Nauata, N., Furukawa, Y.: Structured outdoor architecture reconstruction by exploration and classification. In: IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12407–12415 (2021)
[41]
Zheng J, Zhang J, Li J, Tang R, Gao S, and Zhou Z Vedaldi A, Bischof H, Brox T, and Frahm J-M Structured3D: a large photo-realistic dataset for structured 3D modeling Computer Vision – ECCV 2020 2020 Cham Springer 519-535
[42]
Zheng, Z., Li, J., Zhu, L., Li, H., Petzold, F., Tan, P.: GAT-CADNet: graph attention network for panoptic symbol spotting in CAD drawings. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11737–11746 (2022)
[43]
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (ICLR) (2020)
Index Terms
- PolyRoom: Room-Aware Transformer for Floorplan Reconstruction
Index terms have been assigned to the content through auto-classification.
Recommendations
An Effective Floorplan-Guided Placement Algorithm for Large-Scale Mixed-Size Designs
In this article we propose an effective algorithm flow to handle modern large-scale mixed-size placement, both with and without geometry constraints. The basic idea is to use floorplanning to guide the placement of objects at the global level. The flow ...
Constraint-driven floorplan repair
DAC '06: Proceedings of the 43rd annual Design Automation ConferenceFloorplanning algorithms have traditionally underperformed experienced designers, even when relatively simple interconnect metrics are concerned. However, the sheer scale of modern systems on chip makes an all-manual design flow infeasible. In this ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2024
568 pages
ISBN:978-3-031-72972-0
DOI:10.1007/978-3-031-72973-7
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 November 2024
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 10 Nov 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in