GANCompress: GAN-Enhanced Neural Image Compression with Binary Spherical Quantization

TL;DR

GANCompress introduces a neural image compression method combining Binary Spherical Quantization and GANs, achieving high compression ratios with minimal perceptual loss and faster processing, outperforming traditional codecs on standard benchmarks.

Contribution

This paper presents a novel neural compression framework integrating BSQ with GANs, enhancing efficiency, perceptual quality, and adaptability over existing methods.

Findings

Reduces file sizes by up to 100x with minimal visual distortion.

Outperforms H.264 in perceptual metrics by 12-15%.

Sets new state-of-the-art on ImageNet-1k and COCO2017 benchmarks.

Abstract

The exponential growth of visual data in digital communications has intensified the need for efficient compression techniques that balance rate-distortion performance with computational feasibility. While recent neural compression approaches have shown promise, they still struggle with fundamental challenges: preserving perceptual quality at high compression ratios, computational efficiency, and adaptability to diverse visual content. This paper introduces GANCompress, a novel neural compression framework that synergistically combines Binary Spherical Quantization (BSQ) with Generative Adversarial Networks (GANs) to address these challenges. Our approach employs a transformer-based autoencoder with an enhanced BSQ bottleneck that projects latent representations onto a hypersphere, enabling efficient discretization with bounded quantization error. This is followed by a specialized GAN architecture incorporating frequency-domain attention and color consistency optimization. Experimental results demonstrate that GANCompress achieves substantial improvement in compression efficiency -- reducing file sizes by up to 100x with minimal visual distortion. Our method outperforms traditional codecs like H.264 by 12-15% in perceptual metrics while maintaining comparable PSNR/SSIM values, with 2.4x faster encoding and decoding speeds. On standard benchmarks including ImageNet-1k and COCO2017, GANCompress sets a new state-of-the-art, reducing FID from 0.72 to 0.41 (43% improvement) compared to previous methods while maintaining higher throughput. This work presents a significant advancement in neural compression technology with promising applications for real-time visual communication systems.