BigSUR

Abstract

Fig. 1. Structured Urban Reconstruction. Given street-level imagery, GIS footprints, and a coarse 3D mesh (left), we formulate a global optimization to automatically fuse these noisy, incomplete, and conflicting data sources to create building footprints (middle: colored horizontal polygons) with profiles (vertical ribbons shown for several footprints) and attached building façades (vertical rectangles). The output encodes a structured urban model (right) including the walls, roof, and associated building elements (e.g., windows, balconies, roof, wall color, etc.). Inset below: A reference aerial image.The creation of high-quality semantically parsed 3D models for dense metropolitan areas is a fundamental urban modeling problem. Although recent advances in acquisition techniques and processing algorithms have resulted in large-scale imagery or 3D polygonal reconstructions, such data-sources are typically noisy, and incomplete, with no semantic structure. In this paper, we present an automatic data fusion technique that produces high-quality structured models of city blocks. From coarse polygonal meshes, street-level imagery, and GIS footprints, we formulate a binary integer program that globally balances sources of error to produce semantically parsed mass models with associated façade elements. We demonstrate our system on four city regions of varying complexity; our examples typically contain densely built urban blocks spanning hundreds of buildings. In our largest example, we produce a structured model of 37 city blocks spanning a total of 1,011 buildings at a scale and quality previously impossible to achieve automatically.

Planar Abstraction and Inverse Rendering of 3D Indoor Environments

“…Given the high-resolution mesh, we need to enforce a strong prior to ultimately synthesize a simplified structure. At a high-level, our approach is similar to urban scene modeling [35], but the essential prior being used is different. For urban buildings, they utilize structural clues from GIS footprints, satellite imagery, and semantic segmentation and infer combinations of sweep-edges.…”

Between Images and Built Form: Automating the Recognition of Standardised Building Components Using Deep Learning

“…For example, Lotte et al (2018) address the issue of transferring labels of rendered images back to their 3D urban models combining CNN and Structure from Motion (SfM). Similarly, Kelly et al (2017) use images and 3D models of urban scenes in combination with deep learning techniques to derive structured models of city blocks, addressing the automatic fusion of street-level imagery, polygonal meshes and GIS building footprints. This paper aims to provide an alternative to the use of more classic machine learning methods previously proposed for CH classification such as traditional RF (not deep RF as in Zhou et.…”

Procedural Roof Generation From a Single Satellite Image

“…Since the seminal paper of Parish and Müller [PM01], numerous works have concentrated on city‐scale modeling [VABW09; AFS ∗ 11], road modeling [CEW ∗ 08; GPMG10], parcel modeling [VKW ∗ 12], building modeling [MWH ∗ 06; WWSR03], and facade modeling [BSW13; MZWG07; SHFH11; ZXJ ∗ 13]. Since it is difficult to define and cumbersome to write detailed procedural models of large areas, many works have focused on automatic creation of procedural models, or inverse procedural modeling, often starting from one or more photographs; for example, city‐scale modeling [VGA ∗ 12; KFWM17; ZSBA20], tree creation [SPK ∗ 14; HBDP17], building modeling [NGA ∗ 16; NBA18; ZWF18], and facade generation [ZMA20]. However, few works have focused on automatically generating procedural roofs from images and almost none from a single image.…”