DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Related Data for: A Functional Magnetic Resonance Imaging Investigation of Hot and Cool Executive Functions in Reward and Competition
No full textHealthy Adults fMRI and T1 data. Preprocessed using spm12
Replication Data for: Mutually reinforcing and transpiration-dependent propagation of H2O2 and variation potential in plants revealed by fiber organic electrochemical transistors
No full textData for publication titled "Mutually reinforcing and transpiration-dependent propagation of H2O2 and variation potential in plants revealed by fiber organic electrochemical transistors
Replication Data for: Modelling Terrestrial Dissolved Organic Carbon and its Effect on the Carbonate System in the Sunda Shelf Seas, Southeast Asia
No full textThis file contains two folders: one with the data displayed in the article and the Supporting Information, and the other one with the scripts to create the figures. The sources of the data are referenced in the article
Replication Data for: Integrated Power Management System for the Next-Generation Internet-of-Things
No full textThis dataset contain raw data of our DC-DC converter prototyp
Related Data for: Late-Holocene sea-level markers preserved in a beach ridge system on Phra Thong Island, Thailand
No full text100 MHz ground penetrating radar (GPR) data were collected from Phra Thong Island, Thailand
Related Data for: Investigating Compound Drought and Hot Extreme Events in Southeast Asia Through Copula Analysis
No full textThis dataset consists of the intensity of univariate extreme indices to quantify compound drought and heatwave extremes (DRHE) events in Southeast Asia. The dataset strictly covers the warm season from 1941-2023. Source: ERA5 Reanalysis dataset
Compositional Generative Model of Unbounded 4D Cities
No full text3D scene generation has garnered growing attention in recent years and has made significant progress. Generating 4D cities is more challenging than 3D scenes due to the presence of structurally complex, visually diverse objects like buildings and vehicles, and heightened human sensitivity to distortions in urban environments. To tackle these issues, we propose CityDreamer4D, a compositional generative model specifically tailored for generating unbounded 4D cities. Our main insights are 1) 4D city generation should separate dynamic objects (e.g., vehicles) from static scenes (e.g., buildings and roads), and 2) all objects in the 4D scene should be composed of different types of neural fields for buildings, vehicles, and background stuff. Specifically, we propose Traffic Scenario Generator and Unbounded Layout Generator to produce dynamic traffic scenarios and static city layouts using a highly compact BEV representation. Objects in 4D cities are generated by combining stuff-oriented and instance-oriented neural fields for background stuff, buildings, and vehicles. To suit the distinct characteristics of background stuff and instances, the neural fields employ customized generative hash grids and periodic positional embeddings as scene parameterizations. Furthermore, we offer a comprehensive suite of datasets for city generation, including OSM, GoogleEarth, and CityTopia. The OSM dataset provides a variety of real-world city layouts, while the Google Earth and CityTopia datasets deliver large-scale, high-quality city imagery complete with 3D instance annotations. Leveraging its compositional design, CityDreamer4D supports a range of downstream applications, such as instance editing, city stylization, and urban simulation, while delivering state-of-the-art performance in generating realistic 4D cities
Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution
No full textFaithful text image super-resolution (SR) is challenging because each character has a unique structure and usually exhibits diverse font styles and layouts. While existing methods primarily focus on English text, less attention has been paid to more complex scripts like Chinese. In this paper, we introduce a high-quality text image SR framework designed to restore the precise strokes of low-resolution (LR) Chinese characters. Unlike methods that rely on character recognition priors to regularize the SR task, we propose a novel structure prior that offers structure-level guidance to enhance visual quality. Our framework incorporates this structure prior within a StyleGAN model, leveraging its generative capabilities for restoration. To maintain the integrity of character structures while accommodating various font styles and layouts, we implement a codebook-based mechanism that restricts the generative space of StyleGAN. Each code in the codebook represents the structure of a specific character, while the vector in StyleGAN controls the character's style, including typeface, orientation, and location. Through the collaborative interaction between the codebook and style, we generate a high-resolution structure prior that aligns with LR characters both spatially and structurally. Experiments demonstrate that this structure prior provides robust, character-specific guidance, enabling the accurate restoration of clear strokes in degraded characters, even for real-world LR Chinese text with irregular layouts. Our code and pre-trained models will be available at https://github.com/csxmli2016/MARCONetPlusPlu
Related Data for: Compound Wind and Precipitation Extremes – Predictions for Southeast Asia Coastal Cities
No full textThis dataset consists of compound precipitation and wind (CPW) extremes days in three cities for each group during the historical climate (1975-2005) and present climate (2006-2023) under the RCP 4.5 scenario. CPW extreme days date entry is written in yyyyddmm format for each city in the same group.
Source:
CORDEX-SEA (MOHC-HadGEMS2-ES
Replication Data for: Observation of Embedded Topology in a Trivial Bulk via Projective Crystal Symmetry
No full textThis repository contains the data and code used for the analyses presented in the manuscript: "Observation of Embedded Topology in a Trivial Bulk via Projective Crystal Symmetry", submitted to Physical Review Letters