Substitutional Neural Image Compression
We describe Substitutional Neural Image Compression (SNIC), a general approach for enhancing any neural image compression model, that requires no data or additional tuning of the trained model. It boosts compression performance toward a flexible distortion metric and enables bit-rate control using a single model instance. The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way. Finding such a substitute is inherently difficult for conventional codecs, yet surprisingly favorable for neural compression models thanks to their fully differentiable structures. With gradients of a particular loss backpropogated to the input, a desired substitute can be efficiently crafted iteratively. We demonstrate the effectiveness of SNIC, when combined with various neural compression models and target metrics, in improving compression quality and performing bit-rate control measured by rate-distortion curves. Empirical results of control precision and generation speed are also discussed.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionSimilar Papers 제목 키워드 기반
Substitutional Alloying Using Crystal Graph Neural Networks
Materials discovery, especially for applications that require extreme operating conditions, requires extensive testing that naturally limits the ability to inquire the wealth of possible compositions. Machine Learning (M…
Covariance Decomposition for Distance Based Species Tree Estimation
In phylogenomics, species-tree methods must contend with two major sources of noise; stochastic gene-tree variation under the multispecies coalescent model (MSC) and finite-sequence substitutional noise. Fast agglomerati…
ImputationGS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes
This paper presents GS-RoadPatching, an inpainting method for driving scene completion by referring to completely reconstructed regions, which are represented by 3D Gaussian Splatting (3DGS). Unlike existing 3DGS inpaint…
Atom identification in bilayer moire materials with Gomb-Net
Moire patterns in van der Waals bilayer materials complicate the analysis of atomic-resolution images, hindering the atomic-scale insight typically attainable with scanning transmission electron microscopy. Here, we repo…
A Foundation Model for Non-Destructive Defect Identification from Vibrational Spectra
Defects are ubiquitous in solids and strongly influence materials' mechanical and functional properties. However, non-destructive characterization and quantification of defects, especially when multiple types coexist, re…