3 papers
cs.MM2025
RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation
Zhiqiang Yuan, Ting Zhang, Peixiang Luo +5
Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker gen…
cs.CV2025
WalkVLM:Aid Visually Impaired People Walking by Vision Language Model
Zhiqiang Yuan, Ting Zhang, Ying Deng +5
Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for…
cs.CV2024
ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation
Ting Zhang, Zhiqiang Yuan, Yeshuang Zhu +1
High-quality animated stickers usually contain transparent channels, which are often ignored by current video generation models. To generate fine-grained animated transparency chan…