SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911030995582976 |
|---|---|
| author | Frisch, Yannik Sivakumar, Ssharvien Kumar Köksal, Çağhan Böhm, Elsa Wagner, Felix Gericke, Adrian Ghazaei, Ghazal Mukhopadhyay, Anirban |
| author_facet | Frisch, Yannik Sivakumar, Ssharvien Kumar Köksal, Çağhan Böhm, Elsa Wagner, Felix Gericke, Adrian Ghazaei, Ghazal Mukhopadhyay, Anirban |
| contents | Surgical simulation offers a promising addition to conventional surgical training. However, available simulation tools lack photorealism and rely on hardcoded behaviour. Denoising Diffusion Models are a promising alternative for high-fidelity image synthesis, but existing state-of-the-art conditioning methods fall short in providing precise control or interactivity over the generated scenes.
We introduce SurGrID, a Scene Graph to Image Diffusion Model, allowing for controllable surgical scene synthesis by leveraging Scene Graphs. These graphs encode a surgical scene's components' spatial and semantic information, which are then translated into an intermediate representation using our novel pre-training step that explicitly captures local and global information.
Our proposed method improves the fidelity of generated images and their coherence with the graph input over the state-of-the-art. Further, we demonstrate the simulation's realism and controllability in a user assessment study involving clinical experts.
Scene Graphs can be effectively used for precise and interactive conditioning of Denoising Diffusion Models for simulating surgical scenes, enabling high fidelity and interactive control over the generated content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion Frisch, Yannik Sivakumar, Ssharvien Kumar Köksal, Çağhan Böhm, Elsa Wagner, Felix Gericke, Adrian Ghazaei, Ghazal Mukhopadhyay, Anirban Computer Vision and Pattern Recognition Machine Learning Surgical simulation offers a promising addition to conventional surgical training. However, available simulation tools lack photorealism and rely on hardcoded behaviour. Denoising Diffusion Models are a promising alternative for high-fidelity image synthesis, but existing state-of-the-art conditioning methods fall short in providing precise control or interactivity over the generated scenes. We introduce SurGrID, a Scene Graph to Image Diffusion Model, allowing for controllable surgical scene synthesis by leveraging Scene Graphs. These graphs encode a surgical scene's components' spatial and semantic information, which are then translated into an intermediate representation using our novel pre-training step that explicitly captures local and global information. Our proposed method improves the fidelity of generated images and their coherence with the graph input over the state-of-the-art. Further, we demonstrate the simulation's realism and controllability in a user assessment study involving clinical experts. Scene Graphs can be effectively used for precise and interactive conditioning of Denoising Diffusion Models for simulating surgical scenes, enabling high fidelity and interactive control over the generated content. |
| title | SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.07945 |