Multi-view 3D surface reconstruction is a longstanding challenge in computer vision. Although recent large-scale reconstruction methods based on 3D Gaussian Splatting (3DGS) achieve impressive novel-view synthesis, producing high-quality surfaces over large scenes remains difficult, due to complex geometry, long optimization, and limited memory. In this paper, we propose a novel yet simple partitioning method to efficiently and faithfully reconstruct large-scale scene surfaces. Our key insight lies in a scene partitioning method based on viewpoint orientation. This partitioning approach ensures that views with similar orientations are jointly involved for more accurate depth estimations, leading to precise surface reconstructions and balanced computation on multiple GPUs in parallel. In addition, we propose a strategy to detect and repair missing regions in the initial point cloud caused by sparse viewpoints or insufficient textures, thereby further improving the geometric quality. Extensive experiments on the GauU-Scene, MatrixCity, and UrbanScene3D datasets demonstrate that our method outperforms the state-of-the-art approaches in surface reconstruction for large-scale scenes. Project page: https://hanl2010.github.io/VOP-GS.
We propose a method for detecting structural changes in a city using images captured from vehicular mounted cameras over traversals at two different times. We first generate 3D point clouds for each traversal from the images and approximate GNSS/INS readings using Structure-from-Motion (SfM). A direct comparison of the two point clouds for change detection is not ideal due to inaccurate geo-location information and possible drifts in the SfM. To circumvent this problem, we propose a deep learning-based non-rigid registration on the point clouds which allows us to compare the point clouds for s…
LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；Futurewei Technologies Inc（未来科技公司）；School of Computer and Information Sciences, The University of Newcastle（计算机与信息科学学院，新castle大学）
City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Zhejiang University（浙江大学）；Fudan University（复旦大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Terminus Technologies Co., Ltd.；Pengcheng Laboratory（鹏城实验室）
SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
National Engineering Laboratory for Video Technology, School of Computer Science, Peking University（国家视频技术工程实验室，计算机科学学院，北京大学）；School of Computer Science, Jilin University（吉林大学计算机科学学院）；Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）
NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits its applicability. While these issues can be addressed by learning a prior over scenes in various forms, previous approaches have been either applied to overly simple scenes or struggling to render unobserved parts. We introduce Laser-NV: a generative model which achieves high modelling capacity, and which is based on a set-valued latent representation modelled by normalizing flows. Similarly to p…
UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstruction
Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；School of Software, Beihang University（北京航空航天大学软件学院）；State Key Laboratory of Media Convergence and Communication, Communication University of China（中国传媒大学媒体融合与传播国家重点实验室）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；Artificial Intelligence Research Center, Lobachevsky State University（洛夫奇夫斯基国立大学人工智能研究中心）
Hochschule Bonn-Rhein-Sieg（波恩-莱茵-锡格应用技术大学）；La Sapienza Università di Roma（罗马第一大学）
NeRF-based techniques fit wide and deep multi-layer perceptrons (MLPs) to a continuous radiance field that can be rendered from any unseen viewpoint. However, the lack of surface and normals definition and high rendering times limit their usage in typical computer graphics applications. Such limitations have recently been overcome separately, but solving them together remains an open problem. We present KiloNeuS, a neural representation reconstructing an implicit surface represented as a signed distance function (SDF) from multi-view images and enabling real-time rendering by partitioning the …
Department of Computer Science and Artificial Intelligence, University of Jeddah（计算机科学与人工智能系，朱德亚大学）；Department of Computer Science and Software Engineering, University of Western Australia（计算机科学与软件工程系，西澳大学）；Department of Data Science, Umm Al-Qura University（数据科学系，乌姆·阿勒·卡拉大学）；Department of Information and Technology Systems, College of Computer Science and Engineering, University of Jeddah（信息与技术系统系，计算机科学与工程学院，朱德亚大学）
Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles
i2CAT Foundation（i2CAT基金会）；University of Klagenfurt（克雷格弗特大学）；Universitat Politècnica de Catalunya（巴塞罗那理工大学）；Faculty of Electrical Engineering and Computing（电气工程与计算学院）；University of Zagreb（扎格雷布大学）；NEC Labs Europe GmbH（NEC欧洲实验室）；ICREA
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
This paper studies image-based geo-localization (IBL) problem using ground-to-aerial cross-view matching. The goal is to predict the spatial location of a ground-level query image by matching it to a large geotagged aerial image database (e.g., satellite imagery). This is a challenging task due to the drastic differences in their viewpoints and visual appearances. Existing deep learning methods for this problem have been focused on maximizing feature similarity between spatially close-by image pairs, while minimizing other images pairs which are far apart. They do so by deep feature embedding …
