Related papers: Structured Semantic 3D Reconstruction (S23DR) Chal…

Three-dimensional (3D) urban models have gained interest because of their applications in many use-cases such as urban planning and virtual reality. However, generating these 3D representations requires LiDAR data, which are not always…

3D urban reconstruction of buildings from remotely sensed imagery has drawn significant attention during the past two decades. While aerial imagery and LiDAR provide higher resolution, satellite imagery is cheaper and more efficient to…

Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception and understanding. In literature, several approaches are…

Numerous prior studies predominantly emphasize constructing relation vectors for individual neighborhood points and generating dynamic kernels for each vector and embedding these into high-dimensional spaces to capture implicit local…

Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe…

We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne LiDAR point clouds lies in that the vertical walls are…

The diversity of building architecture styles of global cities situated on various landforms, the degraded optical imagery affected by clouds and shadows, and the significant inter-class imbalance of roof types pose challenges for designing…

We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently captured by a…

Building models are conventionally reconstructed by building roof points planar segmentation and then using a topology graph to group the planes together. Roof edges and vertices are then mathematically represented by intersecting segmented…

We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. Taking a single-channel photogrammetric digital surface model (DSM) and panchromatic (PAN) image as input, we first filter out…

This paper is a technical report about our submission for the ECCV 2018 3DRMS Workshop Challenge on Semantic 3D Reconstruction \cite{Tylecek2018rms}. In this paper, we address 3D semantic reconstruction for autonomous navigation using…

This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured…

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and…

This paper presents a framework to address the challenges involved in building point cloud cleaning, plane detection, and semantic segmentation, with the ultimate goal of enhancing building modeling. We focus in the cleaning stage on…

3D semantic segmentation is one of the most crucial tasks in driving perception. The ability of a learning-based model to accurately perceive dense 3D surroundings often ensures the safe operation of autonomous vehicles. However, existing…

This report describes the winning solution to the WeatherProof Dataset Challenge (CVPR 2024 UG2+ Track 3). Details regarding the challenge are available at https://cvpr2024ug2challenge.github.io/track3.html. We propose an enhanced semantic…

Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point…

We present a novel method for reconstructing parametric, volumetric, multi-story building models from unstructured, unfiltered indoor point clouds by means of solving an integer linear optimization problem. Our approach overcomes…