CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction

• URL: http://arxiv.org/abs/2304.07072v4
• Date: Tue, 12 Dec 2023 09:06:33 GMT
• Title: CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction
• Authors: Hongbo Tian and Yulong Li and Linzhi Huang and Xu Ling and Yue Yang and Jiani Hu
• Abstract summary: We present an enhanced corner representation method for structured reconstruction. It better reconstructs fine-grained structures, such as adjacent corners and tiny edges. It outperforms the state-of-the-art model by +1.9%@F-1 on Corner and +3.0%@F-1 on Edge.
• Score: 20.04081992616026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Structured reconstruction is a non-trivial dense prediction problem, which extracts structural information (\eg, building corners and edges) from a raster image, then reconstructs it to a 2D planar graph accordingly. Compared with common segmentation or detection problems, it significantly relays on the capability that leveraging holistic geometric information for structural reasoning. Current transformer-based approaches tackle this challenging problem in a two-stage manner, which detect corners in the first model and classify the proposed edges (corner-pairs) in the second model. However, they separate two-stage into different models and only share the backbone encoder. Unlike the existing modeling strategies, we present an enhanced corner representation method: 1) It fuses knowledge between the corner detection and edge prediction by sharing feature in different granularity; 2) Corner candidates are proposed in four heatmap channels w.r.t its direction. Both qualitative and quantitative evaluations demonstrate that our proposed method can better reconstruct fine-grained structures, such as adjacent corners and tiny edges. Consequently, it outperforms the state-of-the-art model by +1.9\%@F-1 on Corner and +3.0\%@F-1 on Edge.

Related papers

• Enhancing Polygonal Building Segmentation via Oriented Corners [0.3749861135832072]
  This paper introduces a novel deep convolutional neural network named OriCornerNet, which directly extracts delineated building polygons from input images. Our approach involves a deep model that predicts building footprint masks, corners, and orientation vectors that indicate directions toward adjacent corners. Performance evaluations conducted on SpaceNet Vegas and CrowdAI-small datasets demonstrate the competitive efficacy of our approach.
  arXiv  Detail & Related papers  (2024-07-17T01:59:06Z)
• 3D Neural Edge Reconstruction [61.10201396044153]
  We introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts 3D edges from the inferred edge points and their directions.
  arXiv  Detail & Related papers  (2024-05-29T17:23:51Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• HiT: Building Mapping with Hierarchical Transformers [43.31497052507252]
  We propose a simple and novel building mapping method with Hierarchical Transformers, called HiT. HiT builds on a two-stage detection architecture by adding a polygon head parallel to classification and bounding box regression heads. Our method achieves a new state-of-the-art in terms of instance segmentation and polygonal metrics compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-18T10:24:25Z)
• RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning [62.86400614141706]
  We propose a new learning model, i.e., Rectangling Rectification Network (RecRecNet) Our model can flexibly warp the source structure to the target domain and achieves an end-to-end unsupervised deformation. Experiments show the superiority of our solution over the compared methods on both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2023-01-04T15:12:57Z)
• HEAT: Holistic Edge Attention Transformer for Structured Reconstruction [36.910604284201355]
  This paper presents a novel attention-based neural network for structured reconstruction. It takes a 2D image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners and classifies edge candidates between corners in an end-to-end manner.
  arXiv  Detail & Related papers  (2021-11-30T06:01:11Z)
• Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions [58.71117402626524]
  We present a novel double-branch encoder architecture for medical image segmentation. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels. The experiments validate the effectiveness of our model on four datasets.
  arXiv  Detail & Related papers  (2021-07-24T02:58:32Z)
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [50.56461318879761]
  We propose Geometry-Disentangled Attention Network (GDANet) for 3D image processing. GDANet disentangles point clouds into contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters.
  arXiv  Detail & Related papers  (2020-12-20T13:35:00Z)
• Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment [8.325327265120283]
  We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. We report state of the art results on stretchable domains alignment in a rapid and stable solution for meshes and cloud of points.
  arXiv  Detail & Related papers  (2020-11-30T12:03:28Z)
• Quantization in Relative Gradient Angle Domain For Building Polygon Estimation [88.80146152060888]
  CNN approaches often generate imprecise building morphologies including noisy edges and round corners. We propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs. Experimental results demonstrate that our method refines CNN output from a rounded approximation to a more clear-cut angular shape of the building footprint.
  arXiv  Detail & Related papers  (2020-07-10T21:33:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.