DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
No full textThe field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called LN3Diff to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image into a structured, compact, and 3D latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation across various datasets. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Our proposed LN3Diff presents a significant advancement in 3D generative modeling and holds promise for various applications in 3D vision and graphics tasks
Replication Data for: Covalency-aided electrochemical CO2 reduction to CO on sulfide-derived Cu-Sb
No full textRelated Data for: Covalency-aided electrochemical CO2 reduction to CO on sulfide-derived Cu-S
Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
No full textInstruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of trust and harm the rights of the original image owners. Watermarking is a common solution to trace such malicious behavior. Unfortunately, instruction-driven image editing can significantly change the watermarked image at the semantic level, making current state-of-the-art watermarking methods ineffective. To remedy it, we propose Robust-Wide, the first robust watermarking methodology against instruction-driven image editing. Specifically, we follow the classic structure of deep robust watermarking, consisting of
the encoder, noise layer, and decoder. To achieve robustness against semantic distortions, we introduce a novel Partial Instruction-driven Denoising Sampling Guidance (PIDSG) module, which consists of a large variety of instruction injections and substantial modifications of images at different semantic levels. With PIDSG, the encoder tends to embed the watermark into more robust and semantic-aware areas, which remains in existence even after severe image editing. Experiments demonstrate that Robust-Wide can effectively extract the watermark from the edited image with a low bit error rate of nearly 2.6% for 64-bit watermark messages. Meanwhile, it only induces a neglectable influence on the visual quality and editability of the original images. Moreover, Robust-Wide holds general robustness against different sampling configurations and other popular image editing methods such as ControlNet-InstructPix2Pix, MagicBrush, Inpainting, and DDIM Inversion. Codes and models are available at https://github.com/hurunyi/Robust-Wide
RaBBiT (Raising Biilingual Babies in Talk)
No full textThe RaBBiT (Raising Bilingual Babies in Talk) initiative aims to provide research-informed guidance on how to raise bilingual children to expecting parents and parents with young children aged 0 to 6. The production of the videos and booklets are supported by the Lee Kuan Yew Fund for Bilingualism (MOE), Singapore. The initiative is led by Dr. Yvonne Tse Crepaldi and supported by a team of experts in bilingualism from Singapore and overseas. They include Prof. Suzy Styles and Prof. Ng Bee Chin from NTU, Prof. Seetha Lakshmi and Prof. Mukhlis Abu Bakar from NIE, and Prof. Elizabeth Lanza from the University of Oslo
Replication Data for: Dirac mass induced by optical gain and loss
No full textExperimental data for the paper "Dirac mass induced by optical gain and loss
The Nanoplasmonic Purcell Effect in Ultrafast and High-Light- Yield Perovskite Scintillators
No full textData for the journal paper (Advanced Materials): The Nanoplasmonic Purcell Effect in Ultrafast and High-Light- Yield Perovskite Scintillator
VToonify
No full textGenerating high-quality artistic portrait videos is an important and desirable task in computer graphics and vision. Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency. In this work, we investigate the challenging controllable high-resolution portrait video style transfer by introducing a novel VToonify framework. Specifically, VToonify leverages the mid- and high-resolution layers of StyleGAN to render high-quality artistic portraits based on the multi-scale content features extracted by an encoder to better preserve the frame details. The resulting fully convolutional architecture accepts non-aligned faces in videos of variable size as input, contributing to complete face regions with natural motions in the output. Our framework is compatible with existing StyleGAN-based image toonification models to extend them to video toonification, and inherits appealing features of these models for flexible style control on color and intensity. This work presents two instantiations of VToonify built upon Toonify and DualStyleGAN for collection-based and exemplar-based portrait video style transfer, respectively. Extensive experimental results demonstrate the effectiveness of our proposed VToonify framework over existing methods in generating high-quality and temporally-coherent artistic portrait videos with flexible style controls
Indicator from the graph Laplacian of stock market time series cross sections can precisely determine the durations of market crashes
No full textThis repository include the processed ultrametric distance matrices data, MATLAB scripts and data holder files (in .mat format) used to generate the results and figures in the PLOS paper with the above title
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
No full textWe present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization
Related data for: Decoding scalp health and microbiome dysbiosis
No full textMicrobial colonization in hair follicles was investigated by direct imaging using scanning electron microscope