DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Replication Data for: Noise constraints for nonlinear exceptional point sensing
No full textJulia codes and numerical data for the paper "Noise constraints for nonlinear exceptional point sensing
Tezos degree distribution and influential players
No full textIn-degree and out-degree distribution and influential players for Tezo
Trajectory attention for fine-grained video motion control
No full textRecent advancements in video generation have been greatly driven by video diffusion models, with camera motion control emerging as a crucial challenge in creating view-customized visual content. This paper introduces trajectory attention, a novel approach that performs attention along available pixel trajectories for fine-grained camera motion control. Unlike existing methods that often yield imprecise outputs or neglect temporal correlations, our approach possesses a stronger inductive bias that seamlessly injects trajectory information into the video generation process. Importantly, our approach models trajectory attention as an auxiliary branch alongside traditional temporal attention. This design enables the original temporal attention and the trajectory attention to work in synergy, ensuring both precise motion control and new content generation capability, which is critical when the trajectory is only partially available. Experiments on camera motion control for images and videos demonstrate significant improvements in precision and long-range consistency while maintaining high-quality generation. Furthermore, we show that our approach can be extended to other video motion control tasks, such as first-frame-guided video editing, where it excels in maintaining content consistency over large spatial and temporal ranges
Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting
No full textRGBA images, with the additional alpha channel, are crucial for any application that needs blending, masking, or transparency effects, making them more versatile than standard RGB images. Nevertheless, existing image inpainting methods are designed exclusively for RGB images. Conventional approaches to transparent image inpainting typically involve placing a background underneath RGBA images and employing a two-stage process: image inpainting followed by image matting. This pipeline, however, struggles to preserve transparency consistency in edited regions, and matting can introduce jagged edges along transparency boundaries. To address these challenges, we propose Trans-Adapter, a plug-and-play adapter that enables diffusion-based inpainting models to process transparent images directly. Trans-Adapter also supports controllable editing via ControlNet and can be seamlessly integrated into various community models. To evaluate our method, we introduce LayerBench, along with a novel non-reference alpha edge quality evaluation metric for assessing transparency edge quality. We conduct extensive experiments on LayerBench to demonstrate the effectiveness of our approach
Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
No full textUnderstanding motion in dynamic environments is critical for autonomous driving, thereby motivating research on class-agnostic motion prediction. In this work, we investigate weakly and self-supervised class-agnostic motion prediction from LiDAR point clouds. Outdoor scenes typically consist of mobile foregrounds and static backgrounds, allowing motion understanding to be associated with scene parsing. Based on this observation, we propose a novel weakly supervised paradigm that replaces motion annotations with fully or partially annotated (1%, 0.1%) foreground/background masks for supervision. To this end, we develop a weakly supervised approach utilizing foreground/background cues to guide the self-supervised learning of motion prediction models. Since foreground motion generally occurs in non-ground regions, non-ground/ground masks can serve as an alternative to foreground/background masks, further reducing annotation effort. Leveraging non-ground/ground cues, we propose two additional approaches: a weakly supervised method requiring fewer (0.01%) foreground/background annotations, and a self-supervised method without annotations. Furthermore, we design a Robust Consistency-aware Chamfer Distance loss that incorporates multi-frame information and robust penalty functions to suppress outliers in self-supervised learning. Experiments show that our weakly and self-supervised models outperform existing self-supervised counterparts, and our weakly supervised models even rival some supervised ones. This demonstrates that our approaches effectively balance annotation effort and performance
The novel quinoline derivative SKA-346 as a KCa3.1 channel selective activator
No full textMain and supplementary figure
Replication Data for: Valley-Hall photonic crystal waveguides under non-Hermitian active defect
No full textMatlab scripts and data to plot the figures in the manuscrip
Effects of Zinc Oxide Nanoparticles on Vat Photopolymerziation
No full textBenchmarking images to observe overcuring, tensile tests and DMA results.
DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting
No full textRecent advances in 3D Gaussian Splatting (3D-GS) have shown remarkable success in representing 3D scenes and generating high-quality, novel views in real-time. However, 3D-GS and its variants assume that input images are captured based on pinhole imaging and are fully in focus. This assumption limits their applicability, as real-world images often feature shallow depth-of-field (DoF). In this paper, we introduce DoF-Gaussian, a controllable depth-of-field method for 3D-GS. We develop a lens-based imaging model based on geometric optics principles to control DoF effects. To ensure accurate scene geometry, we incorporate depth priors adjusted per scene, and we apply defocus-to-focus adaptation to minimize the gap in the circle of confusion. We also introduce a synthetic dataset to assess refocusing capabilities and the model’s ability to learn precise lens parameters. Our framework is customizable and supports various interactive applications. Extensive experiments confirm the effectiveness of our method
Replication Data for: Sea-level variability and vertical land motions in Singapore from tide gauge and GNSS observations
No full textThis dataset contains the vertical position time series from 15 Global Navigation Satellite System (GNSS) stations in Singapore. They include one International GNSS Service (IGS) station (NTUS), one station (SING) maintained by the Earth Observatory of Singapore, and 10 stations from the Singapore Satellite Positioning Reference Network (SiReNT), which is a network operated by the Singapore Land Authority. Five stations (SLOY, SNTU, SNYP, SKEP and SSEK) are no longer operational. SLOY, SNTU and SNYP have been relocated and are now known as SLYG, SNYU and SNPT, respectively. The dataset is produced in the paper titled “Sea-level variability and vertical land motions in Singapore from tide gauge and GNSS observations”