P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images

TL;DR

P2PFormer introduces a transformer-based pipeline for extracting regular building contours from remote sensing images, eliminating the need for post-processing and improving accuracy over previous methods.

Contribution

The paper presents a novel primitive-to-polygon pipeline with a transformer architecture and group queries, enabling direct regular contour extraction without post-processing.

Findings

Achieves state-of-the-art performance on multiple datasets.

Surpasses previous SOTA by 2.7 AP and 6.5 AP75 on CrowdAI.

Effectively segments primitives with improved focus and accuracy.

Abstract

Extracting building contours from remote sensing imagery is a significant challenge due to buildings' complex and diverse shapes, occlusions, and noise. Existing methods often struggle with irregular contours, rounded corners, and redundancy points, necessitating extensive post-processing to produce regular polygonal building contours. To address these challenges, we introduce a novel, streamlined pipeline that generates regular building contours without post-processing. Our approach begins with the segmentation of generic geometric primitives (which can include vertices, lines, and corners), followed by the prediction of their sequence. This allows for the direct construction of regular building contours by sequentially connecting the segmented primitives. Building on this pipeline, we developed P2PFormer, which utilizes a transformer-based architecture to segment geometric primitives and predict their order. To enhance the segmentation of primitives, we introduce a unique representation called group queries. This representation comprises a set of queries and a singular query position, which improve the focus on multiple midpoints of primitives and their efficient linkage. Furthermore, we propose an innovative implicit update strategy for the query position embedding aimed at sharpening the focus of queries on the correct positions and, consequently, enhancing the quality of primitive segmentation. Our experiments demonstrate that P2PFormer achieves new state-of-the-art performance on the WHU, CrowdAI, and WHU-Mix datasets, surpassing the previous SOTA PolyWorld by a margin of 2.7 AP and 6.5 AP75 on the largest CrowdAI dataset