Scalable Residual Laplacian Network for HEVC-compressed Video Restoration
Open Access
- 30 June 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (6) , 1-22
Abstract
We present a novel Convolutional Neural Network that exploits the Laplacian decomposition technique, which is typically used in traditional image processing, to restore videos compressed with the High-Efficiency Video Coding (HEVC) algorithm. The proposed method decomposes the compressed frames into multi-scale frequency bands using the Laplacian decomposition, it restores each band using the ad-hoc designed Multi-frame Residual Laplacian Network (MRLN), and finally recomposes the restored bands to obtain the restored frames. By leveraging the multi-scale frequency representation of compressed frames provided by the Laplacian decomposition, MRLN can effectively reduce the compression artifacts and restore the image details with a reduced computational cost. In addition, our method can be easily instantiated in various versions to control the tradeoff between efficiency and effectiveness, representing a versatile solution for scenarios with constrained computational resources. Experimental results on the MFQEv2 benchmark dataset show that our method achieves the state-of-the-art performance in HEVC-compressed video restoration with a lower model complexity and shorter runtime with respect to existing methods. The project page is available at https://github.com/claudiom4sir/LaplacianVCAR .Keywords
Funding Information
- MUR (Dipartimenti di Eccellenza 2023-2027)
This publication has 43 references indexed in Scilit:
- Online Video Quality Enhancement with Spatial-Temporal Look-Up Tables2024
- Video restoration based on deep learning: a comprehensive surveyArtificial Intelligence Review, 2022
- A quality enhancement network with coding priors for constant bit rate video codingKnowledge-Based Systems, 2022
- Attention mechanisms in computer vision: A surveyComputational Visual Media, 2022
- structure-prior assisted blur-intensity aware efficient video deblurringNeurocomputing, 2022
- Quality enhancement of compressed screen content video by cross-frame information fusionNeurocomputing, 2022
- Attention-based interpolation network for video deblurringNeurocomputing, 2021
- A recurrent video quality enhancement framework with multi-granularity frame-fusion and frame difference based attentionNeurocomputing, 2021
- A quality enhancement framework with noise distribution characteristics for high efficiency video codingNeurocomputing, 2020
- The Laplacian Pyramid as a Compact Image Code1987