A5021316524- Retinal Imaging and Analysis
- Blood properties and coagulation
- Visual perception and processing mechanisms
- Robotics and Sensor-Based Localization
- Natural Language Processing Techniques
- Multimodal Machine Learning Applications
- Retinal Diseases and Treatments
- Ophthalmology and Visual Impairment Studies
- Glaucoma and retinal disorders
- Solar and Space Plasma Dynamics
- Planetary Science and Exploration
- Integrated Circuits and Semiconductor Failure Analysis
- Human Motion and Animation
- Digital Imaging for Blood Diseases
- VLSI and Analog Circuit Testing
- Video Analysis and Summarization
- Diabetes, Cardiovascular Risks, and Lipoproteins
- Physical Unclonable Functions (PUFs) and Hardware Security
- Computer Graphics and Visualization Techniques
- 3D Shape Modeling and Analysis
- Visual Attention and Saliency Detection
- Advanced Vision and Imaging
- Astro and Planetary Science
- Diabetic Foot Ulcer Assessment and Management
Zhejiang University
2024-2025
Fudan University
2024
Chung Yuan Christian University
1994-2005
National Taiwan University Hospital
2003
This paper presents GaussEdit, a framework for adaptive 3D scene editing guided by text and image prompts. GaussEdit leverages Gaussian Splatting as its backbone representation, enabling convenient Region of Interest selection efficient through three-stage process. The first stage involves initializing the Gaussians to ensure high-quality edits. second employs an Adaptive Global-Local Optimization strategy balance global coherence detailed local edits category-guided regularization technique...
Abstract Space optical cameras serve as vital tools for solar observation, mostly employing fixed-focus systems to reduce moving parts and increase system stability. However, with increasing demands maintaining consistent image size satellite orbit distance the sun change has become essential, rendering inadequate. Consequently, zoom are emerging a future trend in space payloads. This paper presents structural design of camera based on existing principles. First, several common transmission...
Identifying points of interest (POIs) on the surface 3D shapes is a significant challenge in geometric processing research. The complex connection between POIs and their descriptors, combined with small percentage shape, makes detecting any given shape highly challenging task. Existing methods directly detect from entire resulting low efficiency accuracy. Therefore, we propose novel multi-modal POI detection method using coarse-to-fine approach, key idea reducing data complexity enabling...
Hardware Trojans (HTs) are a longstanding threat to secure computation. Among different models, it is the fabrication-time insertion of additional malicious logic directly into layout integrated circuits (ICs) that constitutes most versatile, yet challenging scenario, for both attackers and defenders.Here, we present large-scale, first-of-its-kind community effort through red-versus-blue teaming thoroughly explores this threat. Four independently competing blue teams 23 IC designers in total...
The images of corneal endothelium cells obtained from specular microscopes are blurred and obscure. We use adaptive local process lowpass filter to enhance the contrast reduce background noise. A special matched is designed detect edges cell borders. Then by applying thinning technique line tracing rules, borders can be correctly identified. This algorithm provides quantitative informations size, density, shape which concerning general status, viability, functional reserve this important layer.
An IBM-PC/AT system with an enhanced graphics adapter has been interfaced a stereoviewer of Nintendo family game to provide method clinical evaluation stereoacuity by binocular dissociation. The is synchronized two digitally generated stereo patterns, which are displayed on color monitor alternately. amount disparity in the patterns interactively changed and recorded through IBM-PC/AT. can also show pictures each eye be used test time separation for motor fusion.< <ETX...