Y Bao, W Tan, M Li, F Meng, Y Liang - Signal Processing, 2025 - Elsevier
Abstract Neural Image Compression (NIC) has made significant strides in recent years. However, the existing NIC methods demonstrate instability issues during iterative re …
We introduce a learning-based CNN architecture for both pre-and post-processing in conjunction with the standard JPEG codec to enhance compression artifact removal. Our …
H Li, S Chen, NML Hossain, M Trocan… - arXiv preprint arXiv …, 2024 - arxiv.org
Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance …
P Qin, Y Bao, F Meng, W Tan, C Li… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
In recent years, with the development of the field of learned image compression, numerous models with excellent rate-distortion performance have emerged. However, the …