Bundle Pooling for Polygonal Architecture Segmentation Problem
This paper introduces a polygonal architecture segmentation problem, proposes bundle-pooling modules for line structure reasoning, and demonstrates a virtual remodeling application that produces production quality results. Given a photograph of a house with a few vanishing point candidates, we decompose the house into a set of architectural components, each of which is represented as a simple geometric primitive. A bundle-pooling module pools convolutional features along a bundle of line segments (e.g., a family of vanishing lines) and fuses the bundle of features to determine polygonal boundaries or assign a corresponding vanishing point. Qualitative and quantitative evaluations demonstrate significant improvements over the existing techniques based on our metric and benchmark dataset. We will share the code and data for further research.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Instance Segmentation With Mask-Supervised Polygonal Boundary Transformers
In this paper, we present an end-to-end instance segmentation method that regresses a polygonal boundary for each object instance. This sparse, vectorized boundary representation for objects, while attractive in many…
Instance SegmentationSegmentationSemantic SegmentationDirect White Matter Bundle Segmentation using Stacked U-Nets
The state-of-the-art method for automatically segmenting white matter bundles in diffusion-weighted MRI is tractography in conjunction with streamline cluster selection. This process involves long chains of processing st…
Image SegmentationSegmentationSemantic SegmentationRe:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing
While most state-of-the-art instance segmentation methods produce pixel-wise segmentation masks, numerous applications demand precise vector polygons of detected objects instead of rasterized output. This paper propo…
Graph Neural NetworkInstance SegmentationScene ParsingSemantic Segmentation+1Anatomically-Informed Multiple Linear Assignment Problems for White Matter Bundle Segmentation
Segmenting white matter bundles from human tractograms is a task of interest for several applications. Current methods for bundle segmentation consider either only prior knowledge about the relative anatomical position o…
AnatomyPositionSegmentationAn Object Aware Hybrid U-Net for Breast Tumour Annotation
In the clinical settings, during digital examination of histopathological slides, the pathologist annotate the slides by marking the rough boundary around the suspected tumour region. The marking or annotation is general…
Deep LearningInstance SegmentationSegmentationSemantic Segmentation