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: RIS-assisted hybrid FSO/THz system with diversity combining schemes: A performance analysis
No full textMATLAB source code the publication title: "RIS-assisted hybrid FSO/THz system with diversity combining schemes: A performance analysis"
These code will produce the outage probability and Bit error rate with asymptotic plots for the above pape
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
No full textGenerating high-quality 3D assets from a given image is highly desirable in various applications such as AR/VR. Recent advances in single-image 3D generation explore feed-forward models that learn to infer the 3D model of an object without optimization. Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects. In this work, we present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. 1) We first perform an in-depth analysis of this ``multi-object gap'' from both model and data perspectives. 2) Next, with reconstructed 3D models of different objects, we seek to adjust their sizes, rotation angles, and locations to create a 3D asset that matches the given image. 3) To automate this process, we apply spatially-aware score distillation sampling (SSDS) from pretrained diffusion models to guide the positioning of objects. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling, and thus achieves more accurate results. Extensive experiments validate ComboVerse achieves clear improvements over existing methods in generating compositional 3D assets
StructLDM: Structured Latent Diffusion for 3D Human Generation
No full textRecent 3D human generative models have achieved remarkable progress by learning 3D-aware GANs from 2D images. However, existing 3D human generative methods model humans in a compact 1D latent space, ignoring the articulated structure and semantics of human body topology. In this paper, we explore more expressive and higher-dimensional latent space for 3D human modeling and propose StructLDM, a diffusion-based unconditional 3D human generative model that is learned from 2D images. StructLDM solves the challenges imposed due to the high-dimensional growth of latent space with three key designs: 1) A semantic structured latent space defined on the dense surface manifold of a statistical human body template. 2) A structured 3D-aware auto-decoder that factorizes the global latent space into several semantic body parts parameterized by a set of conditional structured local NeRFs anchored to the body template, which embeds the properties learned from the 2D training data and can be decoded to render view-consistent humans under different poses and clothing styles. 3) A structured latent diffusion model for generative human appearance sampling. Extensive experiments validate StructLDM's state-of-the-art generation performance and illustrate the expressiveness of the structured latent space over the well-adopted 1D latent space. Notably, StructLDM enables different levels of controllable 3D human generation and editing, including pose/view/shape control, and high-level tasks including compositional generations, part-aware clothing editing, 3D virtual try-on, etc
Related Data for: Cation-Conduction Dominated Hydrogels for Durable Zinc-Iodine Batteries
No full textZinc–iodine batteries have the potential to offer high energy-density aqueous energy storage, but their lifetime is limited by the rampant dendrite growth and the concurrent parasite side reactions on the Zn anode, as well as the shuttling of polyiodides. Herein, a cation-conduction dominated hydrogel electrolyte is designed to holistically enhance the stability of both zinc anode and iodine cathode. In this hydrogel electrolyte, anions are covalently anchored on hydrogel chains, and the major mobile ions in the electrolyte are restricted to be Zn2+. Specifically, such a cation-conductive electrolyte results in a high zinc ion transference number (0.81) within the hydrogel and guides epitaxial Zn nucleation. Furthermore, the optimized Zn2+ solvation structure and the reconstructed hydrogen bond networks on hydrogel chains contribute to the reduced desolvation barrier and suppressed corrosion side reactions. On the iodine cathode side, the electrostatic repulsion between negative sulfonate groups and polyiodides hinders the loss of the iodine active material. This all-round electrolyte design renders zinc–iodine batteries with high reversibility, low self-discharge, and long lifespan
Related Data for: On the Performance of Hybrid THz/FSO System
No full textMATLAB source code the publication title: "On the Performance of Hybrid THz/FSO System"
These code will produce the outage probability plots for the above pape
Related data for: Genetic regulation of injury induced heterotopic ossification in adult zebrafish
No full textGenome-wide bulk RNA sequencing (RNASeq) of contused muscle from the caudal peduncle region of zebrafish at four time points: No injury (Control), 24 hours after single injury (SI), 24 hours after multiple injuries (MI), and 5 days after multiple injuries (D5MI). Dataset contains RNASeq FASTQ files
Data for Project: Heterologous Production Of Cannabinoids In Proprietary Streptomyces Hosts
No full textEnclosed here are genome sequencing data for the two microbial chassis, protocols, methods, and other chemical and biochemical data
Replication Data for: 150 Gbps THz Chipscale Topological Photonic Diplexer
No full textPhotonic diplexers are being widely investigated for high data transfer rates in on-chip communication. However, dividing the available spectrum into non-overlapping multicarrier frequency sub-bands has remained a challenge in designing frequency-selective time-invariant channels. Here, we report an on-chip topological diplexer exhibiting terahertz frequency band filtering through Klein tunnelling of topological edge modes. The silicon topological diplexer chip facilitates two high-speed channels with quadrature amplitude modulation (QAM) over a broad bandwidth of 12.5 GHz each. These channels operate at carrier frequencies of 305 GHz and 321.6 GHz, achieving a combined diplexer capacity of 150 Gbit/s. To ensure minimal interference between adjacent channels, a guard band is implemented. Topologically protected edge modes suppress the frequency selective fading of the broadband signals and hold promise for diverse integrated photonic applications spanning terahertz and telecommunication realms, including the design of lossless topological multiplexers, interconnects, antennas, and modulators for the sixth to X generation (6G to XG) wireless
EdgeSAM
No full textWe present EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. Our approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture, better suited for edge devices. We carefully benchmark various distillation strategies and demonstrate that taskagnostic encoder distillation fails to capture the full knowledge embodied in SAM. To overcome this bottleneck, we include both the prompt encoder and mask decoder in the distillation process, with box and point prompts in the loop, so that the distilled model can accurately capture the intricate dynamics between user input and mask generation. To mitigate dataset bias issues stemming from point prompt distillation, we incorporate a lightweight module within the encoder. As a result, EdgeSAM achieves a 37-fold speed increase compared to the original SAM, and it also outperforms MobileSAM/EfficientSAM, being over 7 times as fast when deployed on edge devices while enhancing the mIoUs on COCO and LVIS by 2.3/1.5 and 3.1/1.6, respectively. It is also the first SAM variant that can run at over 30 FPS on an iPhone 14
Aceh Geohazards Data
No full textRaw data from archaeological survey of coastal Aceh, Indonesia to study paleo tsunami impact on past societies