Zillow Indoor Dataset: Annotated Floor Plans With 360° Panoramas and 3D Room Layouts

Cruz, Steve; Hutchcroft, Will; Li, Yuguang; Khosravan, Naji; Boyadzhiev, Ivaylo; Kang, Sing Bing

doi:10.1109/cvpr46437.2021.00217

Cited by 47 publications

(42 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We implement LGT-Net using PyTorch [17] and use the Adam optimizer [14] with β 1 = 0.9, β 2 = 0.999, and the learning rate is set to 0.0001. We train the network on a single NVIDIA GTX 1080 Ti GPU for 200 epochs on ZInD [4] dataset and 1000 epochs on other datasets, with batch size of 6. We adopt the same data augmentation approaches mentioned in Horizon-Net [23], including standard left-right flipping, panoramic horizontal rotation, luminance change, and pano stretch during training.…”

Section: Methodsmentioning

confidence: 99%

“…ZInD To the best of our knowledge, ZInD [4] dataset is currently the largest dataset with room layout annotations. It better mimics the real-world data distribution since it includes cuboid, more general Manhattan, non-Manhattan, and non-flat ceilings layouts.…”

Section: Datasetsmentioning

confidence: 99%

“…In order to demonstrate the effectiveness of our proposed approach, we conduct extensive experiments on benchmark datasets, including ZInD [4] dataset. Meanwhile, we conduct ablation study on MatterportLayout [33] dataset in the following aspects: loss function, network architecture, and position embedding of Transformer to demonstrate the effectiveness of each component.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

Jiang¹,

Xu²,

Zhao³

2022

Preprint

View full text Add to dashboard Cite

3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizondepth along with room height can obtain omnidirectionalgeometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planargeometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets. The code is publicly available at https: //github.com/zhigangjiang/LGT-Net.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

Jiang¹,

Xu²,

Zhao³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Datasets We propose to use 2D-3D-S [1] and ZInD [4] as commonly used or recently released datasets for experiments. In 2D-3D-S, all panorama images from the same room are mutually visible and grouped together as related views.…”

Section: Comparisonmentioning

confidence: 99%

“…Comparisons on the 2D-3D-Semantics Dataset (2D-3D-S) [1] and Zillow Indoor Dataset (ZInD) [4] show that we significantly improve the geometric accuracy of the 3D layout reconstruction. Specifically, we achieve a significant improvement of 21.7% and 20.6% in terms of depth root mean square error (RMSE) on the 2D-3D-S and ZInD datasets.…”

Section: Introductionmentioning

confidence: 98%

MVLayoutNet:3D layout reconstruction with multi-view panoramas

Hu¹,

Duan²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present MVLayoutNet, an end-to-end network for holistic 3D reconstruction from multi-view panoramas. Our core contribution is to seamlessly combine learned monocular layout estimation and multi-view stereo (MVS) for accurate layout reconstruction in both 3D and image space. We jointly train a layout module to produce an initial layout and a novel MVS module to obtain accurate layout geometry. Unlike standard MVSNet [32], our MVS module takes a newly-proposed layout cost volume, which aggregates multi-view costs at the same depth layer into corresponding layout elements. We additionally provide an attention-based scheme that guides the MVS module to focus on structural regions. Such a design considers both local pixel-level costs and global holistic information for better reconstruction. Experiments show that our method outperforms state-of-the-arts in terms of depth rmse by 21.7% and 20.6% on the 2D-3D-S [1] and ZInD [4] datasets. Finally, our method leads to coherent layout geometry that enables the reconstruction of an entire scene.

show abstract

PanoFormer: Panorama Transformer for Indoor 360$$^{\circ }$$ Depth Estimation

Shen

Lin

Liao

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these datadriven approaches impose an urgent demand for massive data annotations, which are laborious and time-consuming. For the first problem, we propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. DOPNet consists of three modules that are integrated to deliver distortion-free, semantics-clean, and detail-sharp disentangled representations, which benefit the subsequent layout recovery. For the second problem, we present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Concretely, we introduce an optimization strategy for decision-level layout analysis and a 1D cost volume construction method for feature-level multi-view aggregation, both of which are designed to fully exploit the geometric consistency across multiple perspectives. The optimizer provides a reliable set of pseudo-labels for network training, while the 1D cost volume enriches each view with comprehensive scene information derived from other perspectives. Extensive experiments demonstrate that our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks.

show abstract

Zillow Indoor Dataset: Annotated Floor Plans With 360° Panoramas and 3D Room Layouts

Cited by 47 publications

References 42 publications

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

MVLayoutNet:3D layout reconstruction with multi-view panoramas

PanoFormer: Panorama Transformer for Indoor 360$$^{\circ }$$ Depth Estimation

Contact Info

Product

Resources

About