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: Magic wavelength at 477 nm for the strontium clock transition
No full textData for the 477nm magic wavelength pape
Replication Data for: Learning Cache Coherence Traffic for NoC Routing Design
No full textThe dataset includes the source codes and README file for implementing the design presented in the paper 'Learning Cache Coherence Traffic for NoC Routing Design'
Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding
No full textWe introduce the Video Thinking Test (Video-TT), a benchmark designed to assess if video LLMs can interpret real-world videos as effectively as humans. Video-TT 1) differentiates between errors due to inadequate frame sampling and genuine gaps in understanding complex visual narratives, and 2) evaluates robustness against natural adversarial questions. Video-TT comprises 1,000 YouTube Shorts videos, each with one open-ended question and four adversarial questions that probe visual and narrative complexity. Our evaluation shows a significant gap between video LLMs and human performance, underscoring the need for benchmarks like Video-TT to advance video understanding
Replication Data for: High normal stress promoted supershear rupture during the 2023 Mw 7.8 Kahramanmaraş earthquake
No full text1. The anisotropic crustal velocity model for the 2023 Mw 7.8 Kahramanmaraş earthquake region
2. Travel-time data used to build the anisotropic crustal velocity model
Replication Data for: Subwavelength photonic skyrmions propagating without diffraction
No full textExperimental measurement of complex amplitude for different propagation distances. Experimental measurement of complex amplitude at the focal plane for different values of the spin angular momentum charge
Replication Data for: The Ye-U Fault: A Blind Fault Beneath the Central Myanmar Basin Revealed by a High-Resolution Catalog From the 2019 Mw 5.4 Ye-U Earthquake Sequence
No full textRaw waveform data for mainshock and aftershocks of the 2019 Mw 5.4 Ye-U earthquake sequence, recorded by EOS-DMH-MEC stations and a temporary array of short-period seismic nodes. See readme.txt for further details
3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
No full textDespite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model generation are restricted to low resolutions with suboptimal multi-view consistency. In this study, we present a novel 3D enhancement pipeline, dubbed 3DEnhancer, which employs a multi-view latent diffusion model to enhance coarse 3D inputs while preserving multi-view consistency. Our method includes a pose-aware encoder and a diffusion-based denoiser to refine low-quality multi-view images, along with data augmentation and a multi-view attention module with epipolar aggregation to maintain consistent, high-quality 3D outputs across views. Unlike existing video-based approaches, our model supports seamless multi-view enhancement with improved coherence across diverse viewing angles. Extensive evaluations show that 3DEnhancer significantly outperforms existing methods, boosting both multi-view enhancement and per-instance 3D optimization tasks
MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
No full textRecently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists.
Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes.
By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods
Replication Data for: Confocal images of optodroplet system of various c-MYC constructs
No full textThis data contains raw confocal images of optodroplet system of various c-MYC constructs as well as negative and positive controls