G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917492689993728 |
|---|---|
| author | Nath, Vishwesh Tejero, Javier G. Kumar, Aravind S. Li, Ruilong Filicori, Filippo Azizian, Mahdi Huver, Sean D. |
| author_facet | Nath, Vishwesh Tejero, Javier G. Kumar, Aravind S. Li, Ruilong Filicori, Filippo Azizian, Mahdi Huver, Sean D. |
| contents | We propose G-SHARP, a commercially compatible, real-time surgical scene reconstruction framework designed for minimally invasive procedures that require fast and accurate 3D modeling of deformable tissue. While recent Gaussian splatting approaches have advanced real-time endoscopic reconstruction, existing implementations often depend on non-commercial derivatives, limiting deployability. G-SHARP overcomes these constraints by being the first surgical pipeline built natively on the GSplat (Apache-2.0) differentiable Gaussian rasterizer, enabling principled deformation modeling, robust occlusion handling, and high-fidelity reconstructions on the EndoNeRF pulling benchmark. Our results demonstrate state-of-the-art reconstruction quality with strong speed-accuracy trade-offs suitable for intra-operative use. Finally, we provide a Holoscan SDK application that deploys G-SHARP on NVIDIA IGX Orin and Thor edge hardware, enabling real-time surgical visualization in practical operating-room settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline Nath, Vishwesh Tejero, Javier G. Kumar, Aravind S. Li, Ruilong Filicori, Filippo Azizian, Mahdi Huver, Sean D. Computer Vision and Pattern Recognition We propose G-SHARP, a commercially compatible, real-time surgical scene reconstruction framework designed for minimally invasive procedures that require fast and accurate 3D modeling of deformable tissue. While recent Gaussian splatting approaches have advanced real-time endoscopic reconstruction, existing implementations often depend on non-commercial derivatives, limiting deployability. G-SHARP overcomes these constraints by being the first surgical pipeline built natively on the GSplat (Apache-2.0) differentiable Gaussian rasterizer, enabling principled deformation modeling, robust occlusion handling, and high-fidelity reconstructions on the EndoNeRF pulling benchmark. Our results demonstrate state-of-the-art reconstruction quality with strong speed-accuracy trade-offs suitable for intra-operative use. Finally, we provide a Holoscan SDK application that deploys G-SHARP on NVIDIA IGX Orin and Thor edge hardware, enabling real-time surgical visualization in practical operating-room settings. |
| title | G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02482 |