EndoGen: Conditional Autoregressive Endoscopic Video Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915406117076992 |
|---|---|
| author | Liu, Xinyu Liu, Hengyu Wang, Cheng Liu, Tianming Yuan, Yixuan |
| author_facet | Liu, Xinyu Liu, Hengyu Wang, Cheng Liu, Tianming Yuan, Yixuan |
| contents | Endoscopic video generation is crucial for advancing medical imaging and enhancing diagnostic capabilities. However, prior efforts in this field have either focused on static images, lacking the dynamic context required for practical applications, or have relied on unconditional generation that fails to provide meaningful references for clinicians. Therefore, in this paper, we propose the first conditional endoscopic video generation framework, namely EndoGen. Specifically, we build an autoregressive model with a tailored Spatiotemporal Grid-Frame Patterning (SGP) strategy. It reformulates the learning of generating multiple frames as a grid-based image generation pattern, which effectively capitalizes the inherent global dependency modeling capabilities of autoregressive architectures. Furthermore, we propose a Semantic-Aware Token Masking (SAT) mechanism, which enhances the model's ability to produce rich and diverse content by selectively focusing on semantically meaningful regions during the generation process. Through extensive experiments, we demonstrate the effectiveness of our framework in generating high-quality, conditionally guided endoscopic content, and improves the performance of downstream task of polyp segmentation. Code released at https://www.github.com/CUHK-AIM-Group/EndoGen. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EndoGen: Conditional Autoregressive Endoscopic Video Generation Liu, Xinyu Liu, Hengyu Wang, Cheng Liu, Tianming Yuan, Yixuan Computer Vision and Pattern Recognition Image and Video Processing Endoscopic video generation is crucial for advancing medical imaging and enhancing diagnostic capabilities. However, prior efforts in this field have either focused on static images, lacking the dynamic context required for practical applications, or have relied on unconditional generation that fails to provide meaningful references for clinicians. Therefore, in this paper, we propose the first conditional endoscopic video generation framework, namely EndoGen. Specifically, we build an autoregressive model with a tailored Spatiotemporal Grid-Frame Patterning (SGP) strategy. It reformulates the learning of generating multiple frames as a grid-based image generation pattern, which effectively capitalizes the inherent global dependency modeling capabilities of autoregressive architectures. Furthermore, we propose a Semantic-Aware Token Masking (SAT) mechanism, which enhances the model's ability to produce rich and diverse content by selectively focusing on semantically meaningful regions during the generation process. Through extensive experiments, we demonstrate the effectiveness of our framework in generating high-quality, conditionally guided endoscopic content, and improves the performance of downstream task of polyp segmentation. Code released at https://www.github.com/CUHK-AIM-Group/EndoGen. |
| title | EndoGen: Conditional Autoregressive Endoscopic Video Generation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2507.17388 |