7 papers
SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
Zhao Wang, Wei Dai, Hongfu Sun +2
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These a…
SAMRI: Segment Any MRI
Zhao Wang, Wei Dai, Thuy Thanh Dao +4
Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for small and clinically critical structu…
CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects
Zhao Wang, Aoxue Li, Lingting Zhu +3
Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generatio…
AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance
Zhao Wang, Hao Wen, Lingting Zhu +3
Character video generation is a significant real-world application focused on producing high-quality videos featuring specific characters. Recent advancements have introduced vario…
Grounded Knowledge-Enhanced Medical Vision-Language Pre-training for Chest X-Ray
Qiao Deng, Zhongzhen Huang, Yunqi Wang +6
Medical foundation models have the potential to revolutionize healthcare by providing robust and generalized representations of medical data. Medical vision-language pre-training h…
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
Lingting Zhu, Guying Lin, Jinnan Chen +4
While Implicit Neural Representations (INRs) have demonstrated significant success in image representation, they are often hindered by large training memory and slow decoding speed…