Facade Segmentation in the Wild

Femiani, John; Para, Wamiq Reyaz; Mitra, Niloy J.; Wonka, Peter

doi:10.48550/arxiv.1805.08634

Cited by 4 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[23] applied FCNs to obtain the most likely label of each pixel, then the results were optimized through Restricted Boltzmann Machines by adopting horizontal and vertical scanlines. [24] proposed three networks to achieve multilabel semantic segmentation results of facade images. DeepFacade [5], [25] adopted a symmetric regularization which includes a rectangle constraint and a detector constraint to incorporate the shape knowledge of facade elements.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

“…In detail, we employ the original atrous spatial pyramid pooling (ASPP) [31] (see Fig. 3) which consists of one 1 × 1 convolution and three 3 × 3 convolutions with rate= (12,24,36), and image-level features (all with 256 channels). The ASPP module collects multi-scale context information only from a few surrounding pixels and cannot capture dense semantics actually.…”

Section: Coarse Semantic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Facade Parsing with Occlusions

2022

KSII TIIS

View full text Add to dashboard Cite

Correct facade image parsing is essential to the semantic understanding of outdoor scenes. Unfortunately, there are often various occlusions in front of buildings, which fails many existing methods. In this paper, we propose an end-to-end deep network for facade parsing with occlusions. The network learns to decompose an input image into visible and invisible parts by occlusion reasoning. Then, a context aggregation module is proposed to collect nonlocal cues for semantic segmentation of the visible part. In addition, considering the regularity of man-made buildings, a repetitive pattern completion branch is designed to infer the contents in the invisible regions by referring to the visible part. Finally, the parsing map of the input facade image is generated by fusing the results of the visible and invisible results. Experiments on both synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art methods in parsing facades with occlusions. Moreover, we applied our method in applications of image inpainting and 3D semantic modeling.

show abstract

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Section: Coarse Semantic Segmentationmentioning

confidence: 99%

Deep Facade Parsing with Occlusions

2022

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…All objects are annotated as rectangles, limited by the image scope in size and position, while overlap is allowed. This dataset has been widely used as benchmark for window detection or fac ¸ade segmentation tasks [64], [65], [66].…”

Section: B Datasetmentioning

confidence: 99%

“…The images are generated automatically by extracting a piecewise planar geometry from about 30 perspective images. The dataset includes 4 classes: wall, door, window, sky and has been widely used for window detection or fac ¸ade segmentation studies [28], [17], [3], [66].…”

Section: B Datasetmentioning

confidence: 99%

Cross Field-Based Segmentation and Learning-Based Vectorization for Rectangular Windows

Zhuo

Tian

Fraundorfer

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Detection and vectorization of windows from building fac ¸ades are important for building energy modeling, civil engineering, and architecture design. However, current applications still face the challenges of low accuracy and lack of automation.In this paper we propose a new two-steps workflow for window segmentation and vectorization from fac ¸ade images. First, we propose a cross field learning-based neural network architecture, which is augmented by a grid-based self-attention module for window segmentation from rectified fac ¸ade images, resulting in pixel-wise window blobs. Second, we propose a regression neural network augmented by Squeeze-and-Excitation (SE) attention blocks for window vectorization. The network takes the segmentation results together with the original fac ¸ade image as input, and directly outputs the position of window corners, resulting in vectorized window objects with improved accuracy. In order to validate the effectiveness of our method, experiments are carried out on four public fac ¸ades image datasets, with results usually yielding a higher accuracy for the final window prediction in comparison to baseline methods on four datasets in terms of IoU score, F1 score, and pixel accuracy.

show abstract

“…Later works like DeepFacade [Liu et al, 2017] and PALKN [Ma et al, 2021] make use of the regular structure of facades to achieve better semantic results. And the work [Femiani et al, 2018] proposes three different network architectures to better dealing with frontal view facade images with varying complexity.…”

Section: Introductionmentioning

confidence: 99%

Building Facade Parsing R-CNN

Wang¹,

Kang²,

Sheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Building facade parsing, which predicts pixel-level labels for building facades, has applications in computer vision perception for autonomous vehicle (AV) driving. However, instead of a frontal view, an on-board camera of an AV captures a deformed view of the facade of the buildings on both sides of the road the AV is travelling on, due to the camera perspective. We propose Facade R-CNN, which includes a transconv module, generalized bounding box detection, and convex regularization, to perform parsing of deformed facade views. Experiments demonstrate that Facade R-CNN achieves better performance than the current state-of-the-art facade parsing models, which are primarily developed for frontal views. We also publish a new building facade parsing dataset derived from the Oxford RobotCar dataset, which we call the Oxford RobotCar Facade dataset. This dataset contains 500 street-view images from the Oxford RobotCar dataset augmented with accurate annotations of building facade objects. The published dataset is available at https://github.com/ sijieaaa/Oxford-RobotCar-Facade

show abstract

Facade Segmentation in the Wild

Cited by 4 publications

References 26 publications

Deep Facade Parsing with Occlusions

Deep Facade Parsing with Occlusions

Cross Field-Based Segmentation and Learning-Based Vectorization for Rectangular Windows

Building Facade Parsing R-CNN

Contact Info

Product

Resources

About