16 citations · 21 across the 11 of their papers we have counts for
11 papers
MultiColor: Image Colorization by Learning from Multiple Color Spaces
Xiangcheng Du, Zhao Zhou, Yanlong Wang +3
Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representa…
Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling
Lintao Zhang, Xiangcheng Du, LeoWu TomyEnrique +3
For image inpainting, the existing Denoising Diffusion Probabilistic Model (DDPM) based method i.e. RePaint can produce high-quality images for any inpainting form. It utilizes a p…
Fine-Grained Scene Image Classification with Modality-Agnostic Adapter
Yiqun Wang, Zhao Zhou, Xiangcheng Du +3
When dealing with the task of fine-grained scene image classification, most previous works lay much emphasis on global visual features when doing multi-modal feature fusion. In oth…
Efficient scene text image super-resolution with semantic guidance
LeoWu TomyEnrique, Xiangcheng Du, Kangliang Liu +3
Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore…
DDT: Dual-branch Deformable Transformer for Image Denoising
Kangliang Liu, Xiangcheng Du, Sijie Liu +3
Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, dir…
Aggregated Text Transformer for Scene Text Detection
Zhao Zhou, Xiangcheng Du, Yingbin Zheng +1
This paper explores the multi-scale aggregation strategy for scene text detection in natural images. We present the Aggregated Text TRansformer(ATTR), which is designed to represen…
Progressive Scene Text Erasing with Self-Supervision
Xiangcheng Du, Zhao Zhou, Yingbin Zheng +3
Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data. Although data syntheti…
Cross-Domain Document Layout Analysis Using Document Style Guide
Xingjiao Wu, Luwei Xiao, Xiangcheng Du +5
The document layout analysis (DLA) aims to decompose document images into high-level semantic areas (i.e., figures, tables, texts, and background). Creating a DLA framework with st…
Document Layout Analysis with Aesthetic-Guided Image Augmentation
Tianlong Ma, Xingjiao Wu, Xin Li +4
Document layout analysis (DLA) plays an important role in information extraction and document understanding. At present, document layout analysis has reached a milestone achievemen…
Document Layout Analysis via Dynamic Residual Feature Fusion
Xingjiao Wu, Ziling Hu, Xiangcheng Du +2
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optic…
Scene Text Recognition with Temporal Convolutional Encoder
Xiangcheng Du, Tianlong Ma, Yingbin Zheng +3
Texts from scene images typically consist of several characters and exhibit a characteristic sequence structure. Existing methods capture the structure with the sequence-to-sequenc…