5 papers
TextWand: A Unified Framework for Scene Text Editing
Shuyu Wang, Zhile Guan, Hongxiu Chen +5
We propose TextWand, a general-purpose framework that unifies scene text removal, generation, and replacement into a single model. By decomposing complex editing tasks into the ato…
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
Xu Jiang, Bin Chen, Gehui Li +3
The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agen…
StableI2I: Spotting Unintended Changes in Image-to-Image Transition
Jiayang Li, Shuo Cao, Xiaohui Li +6
In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. H…
Adaptive Rectangular Convolution for Remote Sensing Pansharpening
Xueyang Wang, Zhixin Zheng, Jiandong Shao +2
Recent advancements in convolutional neural network (CNN)-based techniques for remote sensing pansharpening have markedly enhanced image quality. However, conventional convolutiona…
Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening
Jie Huang, Rui Huang, Jinghao Xu +3
Pansharpening aims to combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. A…