C
Chia-Ming Cheng
Researcher at MediaTek
Publications - 30
Citations - 339
Chia-Ming Cheng is an academic researcher from MediaTek. The author has contributed to research in topics: Structure from motion & Stereo camera. The author has an hindex of 10, co-authored 30 publications receiving 334 citations. Previous affiliations of Chia-Ming Cheng include National Tsing Hua University.
Papers
More filters
Proceedings ArticleDOI
Improved novel view synthesis from depth image with large baseline
TL;DR: A new algorithm is developed for recovering the large disocclusion regions in depth image based rendering (DIBR) systems on 3DTV and a depth-guided exemplar-based image inpainting that combines the structural strengths of the color gradient to preserve the image structure in the restored regions is proposed.
Journal ArticleDOI
Spatio-Temporally Consistent Novel View Synthesis Algorithm From Video-Plus-Depth Sequences for Autostereoscopic Displays
TL;DR: A novel algorithm to generate multiple virtual views from a video-plus-depth sequence for modern autostereoscopic displays with an iterative re-weighted framework to jointly consider intensity and depth consistency in the adjacent frames is proposed.
Journal ArticleDOI
A consensus sampling technique for fast and robust model fitting
Chia-Ming Cheng,Shang-Hong Lai +1 more
TL;DR: A new algorithm is proposed to improve the efficiency and robustness of random sampling consensus (RANSAC) without prior information about the error scale and the preemptive multiple K-th order approximation is developed for efficient model evaluation with unknown error scale.
Proceedings ArticleDOI
An integrated approach to 3D face model reconstruction from video
Chia-Ming Cheng,Shang-Hong Lai +1 more
TL;DR: The proposed face model reconstruction method has the advantages of efficient computation as well as robustness against noises and outliers.
Patent
System and method for obtaining camera parameters from multiple images and computer program products thereof
Tzu-Chieh Tien,Po-Hao Huang,Chia-Ming Cheng,Hao-Liang Yang,Hsiao-Wei Chen,Shang-Hong Lai,Susan Dong,Cheng-Da Liu,Te-Lu Tsai,Jung-Hsin Hsiao +9 more
TL;DR: In this paper, a sequence of original images associated with a target object under circular motion is obtained, and a background image and a foreground image corresponding to the target object within each original image are segmented.