InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation
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_ | 1866909860343316480 |
|---|---|
| author | Lee, Jungmin Hong, Seonghyuk Lee, Juyong Lee, Jaeyoon Choi, Jongwon |
| author_facet | Lee, Jungmin Hong, Seonghyuk Lee, Juyong Lee, Jaeyoon Choi, Jongwon |
| contents | We introduce InsideOut, an extension of 3D Gaussian splatting (3DGS) that bridges the gap between high-fidelity RGB surface details and subsurface X-ray structures. The fusion of RGB and X-ray imaging is invaluable in fields such as medical diagnostics, cultural heritage restoration, and manufacturing. We collect new paired RGB and X-ray data, perform hierarchical fitting to align RGB and X-ray radiative Gaussian splats, and propose an X-ray reference loss to ensure consistent internal structures. InsideOut effectively addresses the challenges posed by disparate data representations between the two modalities and limited paired datasets. This approach significantly extends the applicability of 3DGS, enhancing visualization, simulation, and non-destructive testing capabilities across various domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17864 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation Lee, Jungmin Hong, Seonghyuk Lee, Juyong Lee, Jaeyoon Choi, Jongwon Computer Vision and Pattern Recognition We introduce InsideOut, an extension of 3D Gaussian splatting (3DGS) that bridges the gap between high-fidelity RGB surface details and subsurface X-ray structures. The fusion of RGB and X-ray imaging is invaluable in fields such as medical diagnostics, cultural heritage restoration, and manufacturing. We collect new paired RGB and X-ray data, perform hierarchical fitting to align RGB and X-ray radiative Gaussian splats, and propose an X-ray reference loss to ensure consistent internal structures. InsideOut effectively addresses the challenges posed by disparate data representations between the two modalities and limited paired datasets. This approach significantly extends the applicability of 3DGS, enhancing visualization, simulation, and non-destructive testing capabilities across various domains. |
| title | InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.17864 |