EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866907988957069312 |
|---|---|
| author | Zhu, Lingting Wang, Zhao Cui, Jiahao Jin, Zhenchao Lin, Guying Yu, Lequan |
| author_facet | Zhu, Lingting Wang, Zhao Cui, Jiahao Jin, Zhenchao Lin, Guying Yu, Lequan |
| contents | Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewpoint videos. However, these methods often suffer from time-consuming optimization or inferior quality, limiting their adoption in downstream tasks. Inspired by 3D Gaussian Splatting, a recent trending 3D representation, we present EndoGS, applying Gaussian Splatting for deformable endoscopic tissue reconstruction. Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision with spatial-temporal weight masks to optimize 3D targets with tool occlusion from a single viewpoint, and surface-aligned regularization terms to capture the much better geometry. As a result, EndoGS reconstructs and renders high-quality deformable endoscopic tissues from a single-viewpoint video, estimated depth maps, and labeled tool masks. Experiments on DaVinci robotic surgery videos demonstrate that EndoGS achieves superior rendering quality. Code is available at https://github.com/HKU-MedAI/EndoGS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting Zhu, Lingting Wang, Zhao Cui, Jiahao Jin, Zhenchao Lin, Guying Yu, Lequan Computer Vision and Pattern Recognition Robotics Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewpoint videos. However, these methods often suffer from time-consuming optimization or inferior quality, limiting their adoption in downstream tasks. Inspired by 3D Gaussian Splatting, a recent trending 3D representation, we present EndoGS, applying Gaussian Splatting for deformable endoscopic tissue reconstruction. Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision with spatial-temporal weight masks to optimize 3D targets with tool occlusion from a single viewpoint, and surface-aligned regularization terms to capture the much better geometry. As a result, EndoGS reconstructs and renders high-quality deformable endoscopic tissues from a single-viewpoint video, estimated depth maps, and labeled tool masks. Experiments on DaVinci robotic surgery videos demonstrate that EndoGS achieves superior rendering quality. Code is available at https://github.com/HKU-MedAI/EndoGS. |
| title | EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2401.11535 |