arXiv cs.AI· Dhananjaya Jayasundara, Sudarshan Rajagopalan, Vishal M. Patel·· 14 小时前AI 评分27
SymKL：基于隐式神经表示的统一信号退化度量
SymKL: A Unified Representation-Space Measure of Signal Degradation
AI 导读
SymKL 是一种基于隐式神经表示（INR）的统一全参考信号退化度量，通过对原始参考信号拟合 INR 并用其对角 Fisher 信息刻画表示空间的局部信息几何，再以原始与退化观测下两组参数敏感度分布的对称 KL 散度定义退化分数。
正文 · 原文
Abstract:Quantifying degradation between a pristine signal and its degraded observation is fundamental to signal processing, yet existing full-reference measures are inherently modality-specific. We introduce SymKL, a unified full-reference degradation measure based on implicit neural representations (INRs). An INR is fitted once to the pristine reference and characterized by its diagonal Fisher information, which captures the local information geometry of the learned representation. Evaluating the Fisher information with the pristine reference and a degraded observation yields two parameter-sensitivity profiles whose symmetric KL divergence defines the degradation score. The proposed formulation requires only the reference and degraded observation, without knowledge of the corruption process or degradation severity, making it applicable across images, audio, and 3D data. We further derive an exact closed-form expression for the diagonal Fisher of SIREN, enabling efficient computation. Experiments on image, speech, and volumetric 3D benchmarks demonstrate that SymKL accurately tracks degradation severity, remains monotonic where conventional metrics saturate or fail, and provides a unified modality-agnostic measure of signal degradation. Code will be made publicly available after the review process.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39403 [cs.CV] |
| (or arXiv:2610.39403v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39403 arXiv-issued DOI via DataCite |
Submission history
From: Dhananjaya Jayasundara [view email]
[v1]
Thu, 29 Oct 2026 05:40:24 UTC (2,927 KB)
来源：arXiv cs.AI · arxiv.org