scholarly journals Spline-Based Dense Medial Descriptors for Lossy Image Compression

2021 ◽  
Vol 7 (8) ◽  
pp. 153
Author(s):  
Jieying Wang ◽  
Jiří Kosinka ◽  
Alexandru Telea
Keyword(s):  
Image Compression ◽  
Comprehensive Evaluation ◽  
Super Resolution ◽  
Salient Feature ◽  
Vector Representation ◽  
Smooth Curves ◽  
B Splines ◽  
Significant Interest ◽  
Feature Preserving ◽  
Image Simplification

Medial descriptors are of significant interest for image simplification, representation, manipulation, and compression. On the other hand, B-splines are well-known tools for specifying smooth curves in computer graphics and geometric design. In this paper, we integrate the two by modeling medial descriptors with stable and accurate B-splines for image compression. Representing medial descriptors with B-splines can not only greatly improve compression but is also an effective vector representation of raster images. A comprehensive evaluation shows that our Spline-based Dense Medial Descriptors (SDMD) method achieves much higher compression ratios at similar or even better quality to the well-known JPEG technique. We illustrate our approach with applications in generating super-resolution images and salient feature preserving image compression.

Few Pains, Many Gains: Fast On-device Image Compression through Super Resolution

2021 ◽  
Author(s):  
Xian Zhang ◽  
Guangtao Fu ◽  
Lin Wang ◽  
Zhuqing Jiang ◽  
Aidong Men
Keyword(s):  
Image Compression ◽  
Super Resolution

scholarly journals Fast Mesh Simplification Method for Three-Dimensional Geometric Models with Feature-Preserving Efficiency

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yongzhi Wang ◽  
Jianwen Zheng ◽  
Hui Wang
Keyword(s):  
Three Dimensional ◽  
Energy Operator ◽  
Salient Feature ◽  
3D Models ◽  
Mesh Simplification ◽  
Trade Off ◽  
Geometric Models ◽  
Feature Preserving ◽  
Effectiveness And Efficiency ◽  
Interactive 3D

To avoid excessive details, thus omitting less important content, of three-dimensional (3D) geometric models, this study proposes a fast mesh simplification method based on an energy-operator for 3D geometric models with salient feature-preserving efficiency. The energy-operator can evaluate the smoothness and complexity of the regional mesh in 3D models. Accordingly, it can be directly used to simultaneously reduce the candidate triangle and its three neighboring triangles. The proposed method can dramatically collapse the excessive details in relatively smooth areas and preserve more important salient features during the simplification process. It can also maintain a trade-off between time efficiency and salient feature-preserving accuracy. The effectiveness and efficiency of the new method are demonstrated by comparing it with OpenMesh, which is considered the most popular mesh operation software and is capable of achieving accurate mesh simplification models. The new mesh simplification method based on the energy-operator can provide accurate and concise models for interactive 3D rendering, calculating, simulating, and analyzing.

Optimizing Image Compression With Deep Super-Resolution Techniques

2020 ◽  
Vol 9 (5) ◽  
pp. 91-101
Author(s):  
Sebastien Hamis ◽  
Titus Zaharia ◽  
Olivier Rousseau
Keyword(s):  
Image Compression ◽  
Super Resolution

Feature Preserving Image Compression: A Survey

2006 ◽  
Author(s):  
Osslan Osiris Vergara Villegas ◽  
Raul Pinto Elias ◽  
Vianey Guadalupe Cruz Sanchez
Keyword(s):  
Image Compression ◽  
Feature Preserving

Low bit rates image compression via adaptive block downsampling and super resolution

2016 ◽  
Vol 25 (1) ◽  
pp. 013004 ◽  
Author(s):  
Honggang Chen ◽  
Xiaohai He ◽  
Minglang Ma ◽  
Linbo Qing ◽  
Qizhi Teng
Keyword(s):  
Image Compression ◽  
Super Resolution

Direct Geometry Processing for Telefabrication

2013 ◽  
Vol 13 (4) ◽  
Author(s):  
Yong Chen ◽  
Kang Li ◽  
Xiaoping Qian
Keyword(s):  
Additive Manufacturing ◽  
Three Dimensional ◽  
Salient Feature ◽  
Physical Object ◽  
Geometry Processing ◽  
New Approach ◽  
B Splines ◽  
Geometric Processing ◽  
Scan Data ◽  
Processing Techniques

This paper presents a new approach for telefabrication where a physical object is scanned in one location and fabricated in another location. This approach integrates three-dimensional (3D) scanning, geometric processing of scanned data, and additive manufacturing (AM) technologies. In this paper, we focus on a set of direct geometric processing techniques that enable the telefabrication. In this approach, 3D scan data are directly sliced into layer-wise contours. Sacrificial supports are generated directly from the contours and digital mask images of the objects and the supports for stereolithography apparatus (SLA) processes are then automatically generated. The salient feature of this approach is that it does not involve any intermediate geometric models such as STL, polygons, or nonuniform rational B-splines (NURBS) that are otherwise commonly used in prevalent approaches. The experimental results on a set of objects fabricated on several SLA machines confirm the effectiveness of the approach in faithfully telefabricating physical objects.

Sign in / Sign up

Export Citation Format

Share Document