JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficient

Korea University1, DGIST2, NVIDIA3
CVPR 2024

*Indicates Corresponding Authors

Instead of using a conventional JPEG decoder to refine the high-quality (HQ) image from the low-quality (LQ) image, our JDEC directly decodes the LQ spectrum by learning a continuous spectrum.

Poster Dataset Distillation (PoDD)

Decoding a JPEG bitstream with the proposed JDEC. JDEC consists of an encoder with group spectra embedding, a decoder, and continuous cosine formulation. Inputs of JDEC are as follows: compressed spectra, quantization map. Note that our JDEC does not take images as an input. JDEC formulates latent features into a trainable continuous cosine coefficient as a function of block grid and forward to INR. Therefore, each block shares the estimated continuous cosine spectrum.


We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a high compression rate, inevitably resulting in quality degradation while encoding an image. We have designed a continuous cosine spectrum estimator to address the quality degradation issue that restores the distorted spectrum. By leveraging local DCT formulations, our network has the privilege to exploit dequantization and upsampling simultaneously. Our proposed model enables decoding compressed images directly across different quality factors using a single pre-trained model without relying on a conventional JPEG decoder. As a result, our proposed network achieves state-of-the-art performance in flexible color image JPEG artifact removal tasks.


@INPROCEEDINGS {jdec2024han,
		author = {W.K. Han and S. Im and J. Kim and K.H. Jin},
		booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
		title = {{JDEC}: JPEG Decoding via Enhanced Continuous Cosine Coefficients},
		year = {2024},