InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation
This work enhances visualization, simulation, and non-destructive testing for fields like medical diagnostics, cultural heritage restoration, and manufacturing, but is incremental as it extends an existing method.
The paper tackles the problem of integrating high-fidelity RGB surface details with subsurface X-ray structures in 3D object representation, resulting in InsideOut, an extension of 3D Gaussian splatting that addresses challenges from disparate data representations and limited paired datasets.
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.