11 papers
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
Yufeng Yang, Jianzhuang Liu, Jisheng Chu +4
Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability a…
MagicFight: Personalized Martial Arts Combat Video Generation
Jiancheng Huang, Mingfu Yan, Songyan Chen +2
Amid the surge in generic text-to-video generation, the field of personalized human video generation has witnessed notable advancements, primarily concentrated on single-person sce…
Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation
Mingfu Yan, Jiancheng Huang, Shifeng Chen
Seal-related tasks in document processing-such as seal segmentation, authenticity verification, seal removal, and text recognition under seals-hold substantial commercial importanc…
STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning
Jie Qin, Jiancheng Huang, Limeng Qiao +1
Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understand…
Contrast-Prior Enhanced Duality for Mask-Free Shadow Removal
Jiyu Wu, Yifan Liu, Jiancheng Huang +2
Existing shadow removal methods often rely on shadow masks, which are challenging to acquire in real-world scenarios. Exploring intrinsic image cues, such as local contrast informa…
Leveraging Contrast Information for Efficient Document Shadow Removal
Yifan Liu, Jiancheng Huang, Na Liu +3
Document shadows are a major obstacle in the digitization process. Due to the dense information in text and patterns covered by shadows, document shadow removal requires specialize…