DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
MOWA: Multiple-in-One Image Warping Model
No full textWhile recent image warping approaches achieved remarkable success on existing benchmarks, they still require training separate models for each specific task and cannot generalize well to different camera models or customized manipulations. To address diverse types of warping in practice, we propose a Multiple-in-One image WArping model (named MOWA) in this work. Specifically, we mitigate the difficulty of multi-task learning by disentangling the motion estimation at both the region level and pixel level. To further enable dynamic task-aware image warping, we introduce a lightweight point-based classifier that predicts the task type, serving as prompts to modulate the feature maps for more accurate estimation. To our knowledge, this is the first work that solves multiple practical warping tasks in one single model. Extensive experiments demonstrate that our MOWA, which is trained on six tasks for multiple-in-one image warping, outperforms state-of-the-art task-specific models across most tasks. Moreover, MOWA also exhibits promising potential to generalize into unseen scenes, as evidenced by cross-domain and zero-shot evaluations
Replication Data for: Enhancing Perovskite Solar Cell Stability and Performance via Bulk Passivation with Sulfonium-Based Passivators
No full textDataset for manuscrip
Replication Data for: Selective Templating Growth of Chemically Inert Low-Dimensional Interfaces for Perovskite Solar Cells
No full textAll Source Data files generated or analysed in the related article can be found in this Dataset
Related Data for: Heatmap analysis of modeled coastal tsunamis using different bathymetry data resolutions
No full textThis contains the supplementary file for the manuscript submitted to Geoscience Letter
FashionEngine: Interactive 3D Human Generation and Editing via Multimodal Controls
No full textWe present FashionEngine, an interactive 3D human generation and editing system that creates 3D digital humans via user-friendly multimodal controls such as natural languages, visual perceptions, and hand-drawing sketches. FashionEngine automates the 3D human production with three key components: 1) A pre-trained 3D human diffusion model that learns to model 3D humans in a semantic UV latent space from 2D image training data, which provides strong priors for diverse generation and editing tasks. 2) Multimodality-UV Space encoding the texture appearance, shape topology, and textual semantics of human clothing in a canonical UV-aligned space, which faithfully aligns the user multimodal inputs with the implicit UV latent space for controllable 3D human editing. The multimodality-UV space is shared across different user inputs, such as texts, images, and sketches, which enables various joint multimodal editing tasks. 3) Multimodality-UV Aligned Sampler learns to sample high-quality and diverse 3D humans from the diffusion prior. Extensive experiments validate FashionEngine's state-of-the-art performance for conditional generation/editing tasks. In addition, we present an interactive user interface for our FashionEngine that enables both conditional and unconditional generation tasks, and editing tasks including pose/view/shape control, text-, image-, and sketch-driven 3D human editing and 3D virtual try-on, in a unified framework
Data from: The direct and indirect effects of road verges and urban greening on butterflies in a tropical city-state
No full textThis includes the data file and R-codes for the statistic
Replication Data for: Reconciling record-breaking ocean temperatures within the Singapore Strait in 2023 with satellite and in-situ data
No full textThis dataset contains the supplementary files and data that were used to produce the manuscript titled: "Reconciling record-breaking ocean temperatures within the Singapore Strait in 2023 with satellite and in-situ data"
Replication Data for: Adaptation to hydrostatic pressure shapes proteome dynamics in corrosive sulcate-reducing bacteria
No full textRaw data for the manuscrip
Replication Data for: Exploring the impact of flow dynamics on corrosive biofilms in the deep sea with high-pressure bio-electrochemostasis
No full textThis dataset contains the raw data for the manuscrip
Preprocessed EEG for: Adult-infant neural coupling mediates infants’ selection of socially-relevant stimuli for learning across cultures
No full textSummary: Contains preprocessed EEG data for both adult and infant participants. Detailed EEG preprocessing steps and parameters are described in the paper's method section and supplementary materials.
Related code repository: https://github.com/Baby-Linc-Singapore/BABBLE_CODE/
Detailed file descriptions:
Preprocessed EEG data files - Each participant-adult pair is stored as a single MATLAB file with naming convention PC/S_BABBLE_AR.mat, where P represents participant ID, C/S indicates site (C for one site, S for another), and AR denotes artifact rejection processing. Each file contains the following key variables:
FSamp (200) - Resampling frequency in Hz used for data standardization
FamEEGart (3×1 cell) - Adult EEG data organized by repeated block numbers
StimEEGart (3×1 cell) - Infant EEG data organized by repeated block numbers
Data structure - Each data cell [i] contains block i data, structured as 3 gaze conditions × 3 phrases per block
Processing variables - Additional cells (AccEpoch, TotAcceptedEpochs, TotBadEpochs, TotUnattendedEpochs, eplen) contain intermediate preprocessing records and quality metrics that are not required for subsequent analyse