The article introduces HFUR, a neural network architecture for enhancing compressed video quality by focusing on frequency-based upsampling and iterative refinement. Video compression artifacts are addressed through the proposed modules: ImpFreqUp and HIR. ImpFreqUp utilizes DCT-domain prior to reconstruct loss, while HIR refines feature maps hierarchically. Extensive experiments demonstrate the effectiveness of HFUR in achieving state-of-the-art performance.
In eine andere Sprache
aus dem Quellinhalt
arxiv.org
Wichtige Erkenntnisse aus
by Qianyu Zhang... um arxiv.org 03-19-2024
https://arxiv.org/pdf/2403.11556.pdfTiefere Fragen