Infinicity: Infinite-scale city synthesis
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which
constructs and renders an unconstrainedly large and 3D-grounded environment from …
constructs and renders an unconstrainedly large and 3D-grounded environment from …
Editable scene simulation for autonomous driving via collaborative llm-agents
Scene simulation in autonomous driving has gained significant attention because of its huge
potential for generating customized data. However existing editable scene simulation …
potential for generating customized data. However existing editable scene simulation …
Neural light field estimation for street scenes with differentiable virtual object insertion
We consider the challenging problem of outdoor lighting estimation for the goal of
photorealistic virtual object insertion into photographs. Existing works on outdoor lighting …
photorealistic virtual object insertion into photographs. Existing works on outdoor lighting …
Estimation of building height using a single street view image via deep neural networks
Y Yan, B Huang - ISPRS Journal of Photogrammetry and Remote …, 2022 - Elsevier
Building smart cities requires three-dimensional (3D) modelling to facilitate the planning and
management of built environments. This requirement leads to high demand for data on …
management of built environments. This requirement leads to high demand for data on …
Capturing, reconstructing, and simulating: the urbanscene3d dataset
We present UrbanScene3D, a large-scale data platform for research of urban scene
perception and reconstruction. UrbanScene3D contains over 128k high-resolution images …
perception and reconstruction. UrbanScene3D contains over 128k high-resolution images …
Extreme rotation estimation using dense correlation volumes
We present a technique for estimating the relative 3D rotation of an RGB image pair in an
extreme setting, where the images have little or no overlap. We observe that, even when …
extreme setting, where the images have little or no overlap. We observe that, even when …
Fully convolutional line parsing
We present a one-stage Fully Convolutional Line P arsing network (F-Clip) that detects line
segments from images. The proposed network is very simple and flexible with variations that …
segments from images. The proposed network is very simple and flexible with variations that …
Enhancing point cloud semantic segmentation in the data‐scarce domain of industrial plants through synthetic data
Digitizing existing structures is essential for applying digital methods in architecture,
engineering, and construction. However, the adoption of data‐driven techniques for …
engineering, and construction. However, the adoption of data‐driven techniques for …
Vapid: A rapid vanishing point detector via learned optimizers
Being able to infer 3D structures from 2D images with geometric principles, vanishing points
have been a well-recognized concept in 3D vision research. It has been widely used in …
have been a well-recognized concept in 3D vision research. It has been widely used in …
Inpainting semantic and depth features to improve visual place recognition in the wild
Visual place recognition is one of the core modern computer vision tasks concerned with
identifying location based on the image taken there. Modern state-of-the-art approaches …
identifying location based on the image taken there. Modern state-of-the-art approaches …