Z
Zhibo Chen
Researcher at University of Science and Technology of China
Publications - 374
Citations - 6048
Zhibo Chen is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Image quality. The author has an hindex of 27, co-authored 344 publications receiving 3385 citations. Previous affiliations of Zhibo Chen include Sony Broadcast & Professional Research Laboratories & Microsoft.
Papers
More filters
Proceedings ArticleDOI
No-Reference Light Field Image Quality Assessment Based on Micro-Lens Image
TL;DR: Wang et al. as mentioned in this paper proposed a no-reference light field image quality assessment model based on Micro-Lens Image (LF-QMLI), which first utilized Global Entropy Distribution (GED) and Uniform Local Binary Pattern descriptor (ULBP) to extract features from the MLI, and then pool them together to measure angular consistency.
Book ChapterDOI
FAN: Frequency Aggregation Network for Real Image Super-Resolution
TL;DR: Zhang et al. as discussed by the authors proposed a frequency aggregation network (FAN) to address the real-world image super-resolu-tion problem, which extracted different frequencies of the LR image and passed them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps.
Patent
Method for animating characters, with collision avoidance based on tracing information
TL;DR: In this article, a method for determining a moving direction or moving velocity for a character in a group comprises reading tracing information from a cell in a terrain map on which the character is located, determining if collision avoidance is needed, and if a collision avoiding manoeuvre is necessary then updating the tracing information in the current terrain cell.
Proceedings ArticleDOI
An entropy coding method for floating-point texture coordinates of 3D mesh
TL;DR: This paper investigates the statistical property of texture coordinates of a couple of 3D models and proposes a new entropy coding method to compress the floating-point texture coordinates and uses some reference buffers and proposes an updating scheme as well as a context based arithmetic coding algorithm.
Patent
Image filtering based on structural information
TL;DR: In this paper, the structural information is described by the regions defined through an edge map of the image and the region correlation between the target pixel and a contributing pixel is selected as a structural filtering coefficient.