Quantum Implicit Neural Compression
This work addresses compression efficiency for multimedia signals, offering a domain-specific improvement that is incremental over existing INR methods.
The paper tackles the problem of high-frequency detail degradation in implicit neural representation (INR)-based signal compression by introducing quantum INR (quINR), which leverages quantum neural networks to improve compression efficiency, achieving up to a 1.2dB gain in rate-distortion performance compared to traditional and classic INR-based methods.
Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively low-resolution signals, the accuracy of high-frequency details is significantly degraded with a small model. To improve the compression efficiency of INR, we introduce quantum INR (quINR), which leverages the exponentially rich expressivity of quantum neural networks for data compression. Evaluations using some benchmark datasets show that the proposed quINR-based compression could improve rate-distortion performance in image compression compared with traditional codecs and classic INR-based coding methods, up to 1.2dB gain.