Representing Images in 200 Bytes: Compression via Triangulation

@article{Marwood2018RepresentingII,
  title={Representing Images in 200 Bytes: Compression via Triangulation},
  author={David Marwood and Pascal Massimino and Michele Covell and Shumeet Baluja},
  journal={2018 25th IEEE International Conference on Image Processing (ICIP)},
  year={2018},
  pages={405-409}
}
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints. [] Key Method First, we propose a novel approach for image compression that, unlike commonly used methods, does not rely on block-based statistics. We use an approach based on an adaptive triangulation of the target image, devoting more triangles to high entropy regions of the image. Second, we present a novel algorithm for encoding the triangles. The results show…

Figures from this paper

Learning to Render Better Image Previews
TLDR
A novel method to significantly improve the reconstruction quality of the original image that requires no changes to the encoded information is presented, which triples the amount of semantic-level content preservation while also improving both SSIM and PSNR scores.
A Novel Approach to Transform Bitmap to Vector Image for Data Reliable Visualization considering the Image Triangulation and Color Selection
TLDR
A new approach proposed to transform from bitmaps to vector images, which is based on triangle units and consists of three steps, and one color will represent one triangle for each triangle in order to prevent a vector image from generating too large color discontinuity.
MAGIC: Machine-Learning-Guided Image Compression for Vision Applications in Internet of Things
TLDR
MAGIC, a novel machine learning (ML)-guided image compression framework that judiciously sacrifices the visual quality to achieve much higher compression when compared to traditional techniques, while maintaining accuracy for coarse-grained vision tasks is proposed.
Fast Inpainting-Based Compression: Combining Shepard Interpolation with Joint Inpainting and Prediction
  • Pascal Peter
  • Computer Science
    2019 IEEE International Conference on Image Processing (ICIP)
  • 2019
TLDR
This work proposes a fast and simple codec that combines Shepard interpolation with a novel joint inpainting and prediction approach that can surpass transform-based codecs, in particular for high compression ratios and cartoon-like images.
Compressing Colour Images with Joint Inpainting and Prediction
TLDR
This work proposes the first full vector quantisation mode for an inpainting-based codec that stores only a small codebook of colours, and exploits a luma preference mode which uses higher sparsity in YCbCr colour channels than in the brightness channel.
Leveraging Domain Knowledge using Machine Learning for Image Compression in Internet-of-Things
TLDR
MAGIC, a novel machine learning (ML) guided image compression framework that judiciously sacrifices visual quality to achieve much higher compression when compared to traditional techniques, while maintaining accuracy for coarse-grained vision tasks is proposed.
Efficient Data Optimisation for Harmonic Inpainting with Finite Elements
TLDR
This work replaces the standard finite differences discretisation by a finite element method with triangle elements and proposes highly efficient algorithms for spatial and tonal data optimisation that are several orders of magnitude faster than state-of-the-art methods.
Reconstruction of Smooth 3D Color Functions from Keypoints: Application to Lossy Compression and Exemplar-Based Generation of Color LUTs
Three-dimensional (3D) CLUTs (color lookup tables) are popular digital models used in artistic image and video processing for color grading, simulation of analog films, and more generally the descr...
Neural Image Decompression: Learning to Render Better Image Previews
TLDR
This work presents a novel method to significantly improve the reconstruction quality of the original image with no changes to the encoded information, and achieves higher PSNR and SSIM scores than the original methods, but also yields a substantial increase in semantic-level content preservation.
Learning Sparse Masks for Diffusion-based Image Inpainting
TLDR
By emulating the complete inPainting pipeline with two networks for mask generation and neural surrogate inpainting, this work obtains a model for highly efficient adaptive mask generation that can achieve competitive quality with an acceleration by as much as four orders of magnitude.
...
1
2
...

References

SHOWING 1-10 OF 26 REFERENCES
Variable Rate Image Compression with Recurrent Neural Networks
TLDR
A general framework for variable-rate image compression and a novel architecture based on convolutional and deconvolutional LSTM recurrent networks are proposed, which provide better visual quality than (headerless) JPEG, JPEG2000 and WebP, with a storage size reduced by 10% or more.
Beating the Quality of JPEG 2000 with Anisotropic Diffusion
TLDR
It is demonstrated that it is even possible to beat the quality of the much more advanced JPEG 2000 standard when one uses subdivisions on rectangles and a number of additional optimisations.
Image compression by linear splines over adaptive triangulations
Image compression with anisotropic triangulations
TLDR
Numerical results show that taking into account the anisotropy improves the approximation by isotropic triangulations of complex images.
Dictionary based surveillance image compression
Fractal image compression based on Delaunay triangulation and vector quantization
TLDR
The aim is to reduce the number of comparisons between the two sets of blocks involved in fractal image compression by keeping only the best representative triangles in the domain blocks set.
Clustering-based quantisation for PDE-based image compression
TLDR
This paper interprets the quantisation step as a clustering problem, and shows that the number of colours can be reduced significantly without impacting the reconstruction quality and are negated by an increased coding cost in compression applications.
Satellite Data Compression
  • S. Qian
  • Computer Science, Environmental Science
  • 2013
TLDR
This chapter describes lossless and near-lossless data compression techniques that have been applied to multispectral, hyperspectral and ultraspectral satellite images, as well as the three international standards of satellite data compression.
Image quality assessment: from error visibility to structural similarity
TLDR
A structural similarity index is developed and its promise is demonstrated through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000.
Image compression with neural networks - A survey
  • J. Jiang
  • Computer Science
    Signal Process. Image Commun.
  • 1999
...
1
2
3
...