4 papers
DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos
Yuan Huang, Sijie Zhao, Jing Cheng +2
Stereo video inpainting, which aims to fill the occluded regions of warped videos with visually coherent content while maintaining temporal consistency, remains a challenging open…
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
Yunheng Li, Jing Cheng, Shaoyong Jia +4
This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video tem…
DreamPainter: Image Background Inpainting for E-commerce Scenarios
Sijie Zhao, Jing Cheng, Yaoyao Wu +2
Although diffusion-based image genenation has been widely explored and applied, background generation tasks in e-commerce scenarios still face significant challenges. The first cha…
Beyond Color and Lines: Zero-Shot Style-Specific Image Variations with Coordinated Semantics
Jinghao Hu, Yuhe Zhang, GuoHua Geng +5
Traditionally, style has been primarily considered in terms of artistic elements such as colors, brushstrokes, and lighting. However, identical semantic subjects, like people, boat…