no code implementations • 12 Apr 2024 • Yueh-Cheng Huang, Hsin-Yi Chen, Cheng-Jui Hung, Jen-Hui Chuang, Jenq-Neng Hwang
Confronting the critical challenge of insufficient training data in the field of complex image recognition, this paper introduces a novel 3D viewpoint augmentation technique specifically tailored for wine label recognition.
1 code implementation • 7 Dec 2023 • Ardian Umam, Cheng-Kun Yang, Min-Hung Chen, Jen-Hui Chuang, Yen-Yu Lin
This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation.
no code implementations • 27 May 2023 • Yueh-Cheng Huang, Chen-Tao Hsu, Jen-Hui Chuang
Experimental results show that highly accurate estimation of homography can be obtained efficiently for planar scenes of the HPatches dataset, based on keypoint matching results provided by LoFTR.
no code implementations • 8 Jan 2023 • Cheng-Yen Hsu, Hsin-Yi Chen, Jen-Hui Chuang
Geometry-based camera calibration using principal line is more precise and robust than calibration using optimization approaches; therefore, several researches try to re-derive the principal line from different views of 2D projective geometry to increase alternatives of the calibration process.
no code implementations • 6 Nov 2022 • Yueh-Cheng Huang, Ching-Huai Yang, Chen-Tao Hsu, Jen-Hui Chuang
In computer vision, finding point correspondence among images plays an important role in many applications, such as image stitching, image retrieval, visual localization, etc.
no code implementations • 28 Jun 2022 • Jen-Hui Chuang, Hsin-Yi Chen
Preparing appropriate images for camera calibration is crucial to obtain accurate results.
no code implementations • 18 Aug 2019 • Jen-Hui Chuang, Chih-Hui Ho, Ardian Umam, Hsin-Yi Chen, Mu-Tien Lu, Jenq-Neng Hwang, Tai-An Chen
Camera calibration is a crucial prerequisite in many applications of computer vision.