9 papers · 1 filter
Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery
Tao Yan, Hao Huang, Yiwei Lu +6
Glass surfaces are ubiquitous in daily life, typically appearing colorless, transparent, and lacking distinctive features. These characteristics make glass surface detection a chal…
GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image
Yinghui Wang, Xinyu Zhang, Peng Du
Generating editable, parametric CAD models from a single image holds great potential to lower the barriers of industrial concept design. However, current multi-modal large language…
Occlusion-Aware Self-Supervised Monocular Depth Estimation for Weak-Texture Endoscopic Images
Zebo Huang, Yinghui Wang
We propose a self-supervised monocular depth estimation network tailored for endoscopic scenes, aiming to infer depth within the gastrointestinal tract from monocular images. Exist…
Capsule Endoscopy Image Enhancement for Small Intestinal Villi Clarity
Shaojie Zhang, Yinghui Wang, Peixuan Liu +4
This paper presents, for the first time, an image enhancement methodology designed to enhance the clarity of small intestinal villi in Wireless Capsule Endoscopy (WCE) images. This…
An Error-Matching Exclusion Method for Accelerating Visual SLAM
Shaojie Zhang, Yinghui Wang, Jiaxing Ma +7
In Visual SLAM, achieving accurate feature matching consumes a significant amount of time, severely impacting the real-time performance of the system. This paper proposes an accele…
A Feature Matching Method Based on Multi-Level Refinement Strategy
Shaojie Zhang, Yinghui Wang, Jiaxing Ma +7
Feature matching is a fundamental and crucial process in visual SLAM, and precision has always been a challenging issue in feature matching. In this paper, based on a multi-level f…