Differentiable JPEG: The Devil is in The Details

Publication Date: 1/3/2024

Event: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)

Reference: pp. 4126-4135, 2024

Authors: Christoph Reich, NEC Laboratories America, Inc., Technische Universitat Darmstadt; Biplob Debnath, NEC Laboratories America, Inc.; Deep Patel, NEC Laboratories America, Inc.; Srimat T. Chakradhar, NEC Laboratories America, Inc.

Abstract: JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive review of existing diff. JPEG approaches and identifies critical details that have been missed by previous methods. To this end, we propose a novel diff. JPEG approach, overcoming previous limitations. Our approach is differentiable w.r.t. the input image, the JPEG quality, the quantization tables, and the color conversion parameters. We evaluate the forward and backward performance of our diff. JPEG approach against existing methods. Additionally, extensive ablations are performed to evaluate crucial design choices. Our proposed diff. JPEG resembles the (non-diff.) reference implementation best, significantly surpassing the recent-best diff. approach by 3.47dB (PSNR) on average. For strong compression rates, we can even improve PSNR by 9.51dB. Strong adversarial attack results are yielded by our diff. JPEG, demonstrating the effective gradient approximation. Our code is available at https://github.com/necla-ml/Diff-JPEG.

Publication Link: https://openaccess.thecvf.com/content/WACV2024/html/Reich_Differentiable_JPEG_The_Devil_Is_in_the_Details_WACV_2024_paper.html