![[2602.12306] Quantum walk inspired JPEG compression of images](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.12306] Quantum walk inspired JPEG compression of images
Summary
This article presents a novel JPEG compression method inspired by quantum walks, enhancing traditional techniques through an adaptive quantization framework that optimizes image quality and compression efficiency.
Why It Matters
As image processing continues to evolve, this research offers a significant advancement in JPEG compression technology, potentially improving applications in computer vision and multimedia. The proposed method achieves better image quality while maintaining compatibility with existing JPEG standards, making it relevant for both academic research and practical implementations.
Key Takeaways
- Introduces a quantum-inspired adaptive quantization framework for JPEG compression.
- Achieves average PSNR gains of 3 to 6 dB, enhancing image quality.
- Maintains JPEG compliance, ensuring compatibility with existing systems.
- Evaluated on standard datasets like MNIST, CIFAR10, and ImageNet.
- Utilizes a unified rate distortion objective for improved fidelity and efficiency.
Electrical Engineering and Systems Science > Image and Video Processing arXiv:2602.12306 (eess) [Submitted on 12 Feb 2026] Title:Quantum walk inspired JPEG compression of images Authors:Abhishek Verma, Sahil Tomar, Sandeep Kumar View a PDF of the paper titled Quantum walk inspired JPEG compression of images, by Abhishek Verma and 2 other authors View PDF Abstract:This work proposes a quantum inspired adaptive quantization framework that enhances the classical JPEG compression by introducing a learned, optimized Qtable derived using a Quantum Walk Inspired Optimization (QWIO) search strategy. The optimizer searches a continuous parameter space of frequency band scaling factors under a unified rate distortion objective that jointly considers reconstruction fidelity and compression efficiency. The proposed framework is evaluated on MNIST, CIFAR10, and ImageNet subsets, using Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Bits Per Pixel (BPP), and error heatmap visual analysis as evaluation metrics. Experimental results show average gains ranging from 3 to 6 dB PSNR, along with better structural preservation of edges, contours, and luminance transitions, without modifying decoder compatibility. The structure remains JPEG compliant and can be implemented using accessible scientific packages making it ideal for deployment and practical research use. Comments: Subjects: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision ...