Search Results for author:
Found 28 papers, 7 papers with code
PromptGAR: Flexible Promptive Group Activity Recognition
We present PromptGAR, a novel framework that addresses the limitations of current Group Activity Recognition (GAR) approaches by leveraging multi-modal prompts to achieve both input flexibility and high recognition accuracy.
Deformable Beta Splatting
Notably, for the first time, splatting-based methods outperform state-of-the-art Neural Radiance Fields, highlighting the superior performance and efficiency of DBS for real-time radiance field rendering.
Ranked #1 on
Novel View Synthesis
on NeRF
SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting
Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details.
C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System
Organizations seeking to utilize Large Language Models (LLMs) for knowledge querying and analysis often encounter challenges in maintaining an LLM fine-tuned on targeted, up-to-date information that keeps answers relevant and grounded.
Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework
To this end, the objective of this research is to design and develop a comprehensive and efficient framework for 3D segmentation tasks to assist in 3D data annotation.
Skyeyes: Ground Roaming using Aerial View Images
In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience.
Geometry-aware Feature Matching for Large-Scale Structure from Motion
Our method formulates geometric verification as an optimization problem, guiding feature matching within detector-free methods and using sparse correspondences from detector-based methods as anchor points.
AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field
3D Gaussian Splatting (3DGS) has recently advanced radiance field reconstruction by offering superior capabilities for novel view synthesis and real-time rendering speed.
Empowering Federated Learning for Massive Models with NVIDIA FLARE
In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge.
Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach
Photorealistic style transfer aims to apply stylization while preserving the realism and structure of input content.
Generative AI for Medical Imaging: extending the MONAI Framework
We have implemented these models in a generalisable fashion, illustrating that their results can be extended to 2D or 3D scenarios, including medical images with different modalities (like CT, MRI, and X-Ray data) and from different anatomical areas.
DeepEdit: Deep Editable Learning for Interactive Segmentation of 3D Medical Images
Automatic segmentation of medical images is a key step for diagnostic and interventional tasks.
Co-Speech Gesture Synthesis using Discrete Gesture Token Learning
Synthesizing realistic co-speech gestures is an important and yet unsolved problem for creating believable motions that can drive a humanoid robot to interact and communicate with human users.
MONAI: An open-source framework for deep learning in healthcare
For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e. g. geometry, physiology, physics) of medical data being processed.
NVIDIA FLARE: Federated Learning from Simulation to Real-World
Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data.
MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images
MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike.
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
Specifically, we introduce a synthetic aerial photogrammetry point clouds generation pipeline that takes full advantage of open geospatial data sources and off-the-shelf commercial packages.
Do Gradient Inversion Attacks Make Federated Learning Unsafe?
Federated learning (FL) allows the collaborative training of AI models without needing to share raw data.
Ground material classification for UAV-based photogrammetric 3D data A 2D-3D Hybrid Approach
For ground material segmentation, we utilized an existing convolutional neural network architecture (i. e., 3DMV) which was originally designed for segmenting RGB-D sensed indoor data.
3D photogrammetry point cloud segmentation using a model ensembling framework
In this paper, we introduce a model ensembling framework for segmenting a 3D photogrammetry point cloud into top-level terrain elements (i. e., ground, human-made objects, and vegetation).
Utilizing Satellite Imagery Datasets and Machine Learning Data Models to Evaluate Infrastructure Change in Undeveloped Regions
A goal of this research is to allow automated monitoring for largescale infrastructure projects, such as railways, to determine reliable metrics that define and predict the direction construction initiatives could take, allowing for a directed monitoring via narrowed and targeted satellite imagery requests.
Generating synthetic photogrammetric data for training deep learning based 3D point cloud segmentation models
At I/ITSEC 2019, the authors presented a fully-automated workflow to segment 3D photogrammetric point-clouds/meshes and extract object information, including individual tree locations and ground materials (Chen et al., 2019).
Semantic Segmentation and Data Fusion of Microsoft Bing 3D Cities and Small UAV-based Photogrammetric Data
This paper discusses the next steps in extending our designed data segmentation framework for segmenting 3D city data.
Fully Automated Photogrammetric Data Segmentation and Object Information Extraction Approach for Creating Simulation Terrain
The results showed that 3D mesh trees could be replaced with geo-typical 3D tree models using the extracted individual tree locations.
Photogrammetric point cloud segmentation and object information extraction for creating virtual environments and simulations
Thus, segmenting generated point clouds and meshes and extracting the associated object information is a necessary step.
Privacy-preserving Federated Brain Tumour Segmentation
Due to medical data privacy regulations, it is often infeasible to collect and share patient data in a centralised data lake.
Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale
Deep distributed decision trees and tree ensembles have grown in importance due to the need to model increasingly large datasets.
Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
For this reason search engines often provide a service of advanced matching, which automatically finds additional relevant queries for advertisers to bid on.
