Related papers: HoliCity: A City-Scale Data Platform for Learning …

We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…

This article includes a comprehensive collection of over 800 high-resolution streetlight images taken systematically from India's major streets, primarily in the Chennai region. The images were methodically collected following standardized…

While 3D Gaussian Splatting (3DGS) enables high-quality, real-time rendering for bounded scenes, its extension to large-scale urban environments gives rise to critical challenges in terms of geometric consistency, memory efficiency, and…

Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. Moreover, recent driving datasets primarily provide sparse LiDAR ground truth for images,…

Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range from entertainment domains like movies, where the focus is…

Recent advancements in generative models have enabled 3D urban scene generation from satellite imagery, unlocking promising applications in gaming, digital twins, and beyond. However, most existing methods rely heavily on neural rendering…

Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These…

This paper provides a first milestone in measuring the floorspace of buildings (that is, building footprint and height) for 40 major Chinese cities. The intent is to maximize city coverage and, eventually provide longitudinal data. Doing so…

We introduce the Reality-linked 3D Scenes (R3DS) dataset of synthetic 3D scenes mirroring the real-world scene arrangements from Matterport3D panoramas. Compared to prior work, R3DS has more complete and densely populated scenes with…

Accurate 3D reconstruction of objects with reflective, transparent, or low-texture surfaces still remains notoriously challenging. Such materials often violate key assumptions in multi-view reconstruction pipelines, such as photometric…

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…

This work presents dense stereo reconstruction using high-resolution images for infrastructure inspections. The state-of-the-art stereo reconstruction methods, both learning and non-learning ones, consume too much computational resource on…

Safe motion planning in robotics requires planning into space which has been verified to be free of obstacles. However, obtaining such environment representations using lidars is challenging by virtue of the sparsity of their depth…

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the development of 3D perception, reconstruction, and generation in the real world, we propose…

Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point…

Key points, correspondences, projection matrices, point clouds and dense clouds are the skeletons in image-based 3D reconstruction, of which point clouds have the important role in generating a realistic and natural model for a 3D…

Study of urban form is an important area of research in urban planning/design that contributes to our understanding of how cities function and evolve. However, classical approaches are based on very limited observations and inconsistent…

It has been shown that global scene understanding tasks like layout estimation can benefit from wider field of views, and specifically spherical panoramas. While much progress has been made recently, all previous approaches rely on…

Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private. While research efforts on federated learning have been growing…

The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their…