DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Sit is not lit: Examining the impact of message framing, modality, and peer influence on attitudes and intentions to reduce sedentary behavior
No full textThis is for "Sit is not lit: Examining the impact of message framing, modality, and peer influence on attitudes and intentions to reduce sedentary behavior" pape
First year trends and stats of cryptocurrency
No full textContains month-by-month and year-by-year statistics on number and volume of transactions, number of new wallet addresses as well as day-by-day statistics on number and volume of transactions for Bitcoin, Ethereum, Iotex and Tezos
Related Data for: PESI: Paratope-Epitope Set Interaction for SARS-CoV-2 Neutralization Prediction
No full textThis dataset contains 3 versions of epitope-paratope data and their neutralizing data for the SARS-CoV 2 virus. We pre-processed and annotated antibody-antigen binding data from the Observed Antibody Space (OAS) database to obtain these paratopes and epitopes
Generative Gaussian Splatting for Unbounded 3D City Generation
No full text3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity, a generative Gaussian Splatting framework dedicated to efficiently synthesizing unbounded 3D cities with a single feed-forward pass. Our key insights are two-fold: 1) Compact 3D Scene Representation: We introduce BEV-Point as a highly compact intermediate representation, ensuring that the growth in VRAM usage for unbounded scenes remains constant, thus enabling unbounded city generation. 2) Spatial-aware Gaussian Attribute Decoder: We present spatial-aware BEV-Point decoder to produce 3D Gaussian attributes, which leverages Point Serializer to integrate the structural and contextual characteristics of BEV points. Extensive experiments demonstrate that GaussianCity achieves state-of-the-art results in both drone-view and street-view 3D city generation. Notably, compared to CityDreamer, GaussianCity exhibits superior performance with a speedup of 60 times (10.72 FPS v.s. 0.18 FPS)
Related Data for: Timing of emergence of modern rates of sea-level rise by 1863
No full textThis dataset is a comprehensive open-access database of the paper titled" Timing of emergence of modern rates of sea-level rise by 1863"
Survey on Social Trust in AI
No full textThis dataset results from a cross-country survey in East Asi
Artificial Intelligence Prediction Across 12,000 Samples Shows Widespread Increased Gene-Gene Chromatin Interactions in Cancers that Constitute Therapeutic Vulnerabilities
No full textGene-gene chromatin interactions (GGIs) bring distal genes into close spatial proximity to permit strong co-expression, which could potentially contribute to cancer progression. High-throughput methods like Hi-C are impractical for very large cohort analyses, thus we developed AI4Loop, an Artificial Intelligence (AI) Deep Learning -based tool to predict GGIs using RNA-Seq data. Applying AI4Loop to 12,000 patient samples from the TCGA database across 32 cancer types revealed that GGIs show increased cancer sub-type predictivity compared to RNA-Seq data and demonstrated oncogenic gains of GGIs interaction in almost all cancers examined. To target the therapeutic vulnerability of gain of GGIs in cancers, using low-information RNA expression datasets from the CLUE database, we also constructed a drug-perturbation GGI atlas from 50,000 drug-treated samples to identify and repurposed compounds that disrupt oncogenic GGIs. Notably, we found that the antibiotics eperezolid and radezolid reduced cancer-acquired GGIs, which we confirmed with Hi-C experiment. This work showcases AI-directed research in epigenetics, enhances cancer biology predictivity and can promote wide-range drug repurposing in the future
Arbitrary-steps Image Super-resolution via Diffusion Inversion
No full textThis study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point. Central to our approach is a deep noise predictor to estimate the optimal noise maps for the forward diffusion process. Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result. Compared to existing approaches, our method offers a flexible and efficient sampling mechanism that supports an arbitrary number of sampling steps, ranging from one to five. Even with a single sampling step, our method demonstrates superior or comparable performance to recent state-of-the-art approaches
GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation
No full textWhile 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these challenges, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space. Our framework employs a Variational Autoencoder (VAE) with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information, and incorporates a cascaded latent diffusion model for improved shape-texture disentanglement. The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single/multi-view image inputs. Notably, the newly proposed latent space naturally enables geometry-texture disentanglement, thus allowing 3D-aware editing. Experimental results demonstrate the effectiveness of our approach on multiple datasets, outperforming existing methods in both text- and image-conditioned 3D generation
Replication Data for: Generalized Wigner-Smith analysis of resonance perturbations in arbitrary Q non-Hermitian systems
No full textInteractive Python notebooks to generate data reported in publication: https://doi.org/10.1103/PhysRevResearch.7.01329