TADiSR is a diffusion-based super-resolution model that jointly predicts a text segmentation mask from cross-attention maps, improving text legibility in restored full images.
Ntire 2017 challenge on single image super-resolution: Dataset and study
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
TADiSR is a diffusion-based super-resolution model that jointly predicts a text segmentation mask from cross-attention maps, improving text legibility in restored full images.