Revisiting SVD and Wavelet Difference Reduction for Lossy Image Compression: A Reproducibility Study
Alena Makarova
TL;DR
An independent reproducibility study re-implements a lossy image compression technique that fuses SVD with Wavelet Difference Reduction (WDR) to test claims of superiority over JPEG2000 and standalone WDR. The author identifies missing implementation details (e.g., quantization in the refinement pass and threshold initialization), replicates the original experiments where possible, and extends evaluation to new imagery, including glacier-relevant content. Across replication and new tests, PSNR performance generally does not exceed JPEG2000 or WDR, while SSIM shows only partial improvement in some cases, challenging the original claims. The work emphasizes the importance of transparent algorithmic descriptions and thorough validation across diverse content for reproducibility in image compression research.
Abstract
This work presents an independent reproducibility study of a lossy image compression technique that integrates singular value decomposition (SVD) and wavelet difference reduction (WDR). The original paper claims that combining SVD and WDR yields better visual quality and higher compression ratios than JPEG2000 and standalone WDR. I re-implemented the proposed method, carefully examined missing implementation details, and replicated the original experiments as closely as possible. I then conducted additional experiments on new images and evaluated performance using PSNR and SSIM. In contrast to the original claims, my results indicate that the SVD+WDR technique generally does not surpass JPEG2000 or WDR in terms of PSNR, and only partially improves SSIM relative to JPEG2000. The study highlights ambiguities in the original description (e.g., quantization and threshold initialization) and illustrates how such gaps can significantly impact reproducibility and reported performance.