VSR-HE, a per-frame transformer trained with perceptual and GAN losses, reports improved 4x super-resolution quality on HEVC-compressed conferencing video versus bicubic, EDSR, CVEGAN, and SwinIR.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Compressed Video Super-Resolution based on Hierarchical Encoding
VSR-HE, a per-frame transformer trained with perceptual and GAN losses, reports improved 4x super-resolution quality on HEVC-compressed conferencing video versus bicubic, EDSR, CVEGAN, and SwinIR.