DARNet: Deep Active Ray Network for Building Segmentation
By Dominic Cheng, Renjie Liao, Sanja Fidler, Raquel Urtasun. 2019
131 citations recorded by the source corpus.
In this paper, we propose a Deep Active Ray Network (DARNet) for automatic building segmentation. Taking an image as input, it first exploits a deep convolutional neural network (CNN) as the backbone to predict energy maps, which are further utilized to construct an energy function. A polygon-based contour is then evolved via minimizing the energy function, of which the minimum defines the final segmentation. Instead of parameterizing the contour using Euclidean coordinates, we adopt polar coordinates, i.e., rays, which not only prevents self-intersection but also simplifies the design of the energy function. Moreover, we propose a loss function that directly encourages the contours to match building boundaries. Our DARNet is trained end-to-end by back-propagating through the energy minimization and the backbone CNN, which makes the CNN adapt to the dynamics of the contour evolution. Experiments on three building instance segmentation datasets demonstrate our DARNet achieves either state-of-the-art or comparable performances to other competitors.
Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Remote Sensing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Jitendra Malik
- Ming-Hsuan Yang
- Xiaogang Wang
- Andrew Zisserman
- Trevor Darrell
- Andrea Vedaldi
In Environmental Engineering
- Antonio J. Plaza
- Lior Wolf
- Yuri Boykov
- Demetri Terzopoulos
- Yasutaka Furukawa
- Liangliang Nan
- Fatih Murat Porikli
- Eliya Nachmani
In Remote Sensing
Citations in the corpus
- 3D Instance Segmentation of MVS Buildings (2021, background): “DARNet employs a polar representation of contours to predict contours that are free of self-intersection and a loss function consisting of a data term, a curvature term, and a balloon term, which not only encourages the predicted contours to match ground truth building boundaries but also prefers lo”
- Image Segmentation Using Deep Learning: A Survey (2020, background): “[111] proposed the Deep Active Ray Network (DarNet), which is similar to DSAC, but with a different explicit ACM formulation based on polar coordinates to prevent contour self-intersection.”
- CNN-GCN Aggregation Enabled Boundary Regression for Biomedical Image Segmentation (2020, methodology): “We compare our model with other state-of-the-art methods, including U-Net [22], PolarMask [24], M-Net [6], U-Net++ [27], DANet [7], DARNet [3], DeepLabv3+ [2] through running their open public source code.”
- Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction (2019, methodology): “In remote sensing, most building extraction methods represent a building as a set of pixels [14] or a 1D polygonal loop [2, 6, 20, 7], limiting the output to a building external boundary as a 1D loop.”
- SegDiff: Image Segmentation with Diffusion Probabilistic Models (2021, methodology): “The same augmentations are used as in [7]: random scaling by a factor sampled uniformly in the range [0 .”