5 papers
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
Minxing Luo, Linlong Fan, Wang Qiushi +7
Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image quality and textual readability. T…
MeanFlow Transformers with Representation Autoencoders
Zheyuan Hu, Chieh-Hsin Lai, Ge Wu +2
MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used…
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
Ge Wu, Shen Zhang, Ruijing Shi +9
REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment betwee…
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
Shen Zhang, Siyuan Liang, Yaning Tan +9
Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE),…
Powerful Design of Small Vision Transformer on CIFAR10
Gent Wu
Vision Transformers (ViTs) have demonstrated remarkable success on large-scale datasets, but their performance on smaller datasets often falls short of convolutional neural network…