4D-STDF: Compressed Video Quality Enhancement with 3D Spatio-Temporal Fusion and Deformable Convolution
Open Access
- 10 November 2025
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 491-495
Abstract
Compressed videos frequently present artifacts that compromise visual quality. Deep learning models have demonstrated significant effectiveness in mitigating such distortions. In this study, we introduce 3D-STDF, an architecture based on the well-known Spatio-Temporal Deformable Fusion (STDF) and augmented with 3D convolutions to more effectively model temporal dependencies across video frames. Furthermore, we refine the Quality Enhancement (QE) module by integrating residual blocks, thereby enabling the extraction and representation of more intricate spatial features. Experimental results indicate that models based on the 3D-STDF architecture achieved an overall average improvement of up to 0.607 dB in PSNR, clearly outperforming previous STDF-based solutions.Keywords
This publication has 26 references indexed in Scilit:
- Video restoration based on deep learning: a comprehensive surveyArtificial Intelligence Review, 2022
- Gesture recognition based on deep deformable 3D convolutional neural networksPattern Recognition, 2020
- EDVR: Video Restoration With Enhanced Deformable Convolutional Networks2019
- Video Enhancement with Task-Oriented FlowInternational Journal of Computer Vision, 2019
- Multi-frame Quality Enhancement for Compressed Video2018
- Deformable Convolutional Networks2017
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation2017
- A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding2016
- Compression Artifacts Reduction by a Deep Convolutional Network2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015