RGS-DR: Reflective Gaussian Surfels with Deferred Rendering for Shiny Objects
By: Georgios Kouros, Minye Wu, Tinne Tuytelaars
Potential Business Impact:
Makes shiny objects look real in computer pictures.
We introduce RGS-DR, a novel inverse rendering method for reconstructing and rendering glossy and reflective objects with support for flexible relighting and scene editing. Unlike existing methods (e.g., NeRF and 3D Gaussian Splatting), which struggle with view-dependent effects, RGS-DR utilizes a 2D Gaussian surfel representation to accurately estimate geometry and surface normals, an essential property for high-quality inverse rendering. Our approach explicitly models geometric and material properties through learnable primitives rasterized into a deferred shading pipeline, effectively reducing rendering artifacts and preserving sharp reflections. By employing a multi-level cube mipmap, RGS-DR accurately approximates environment lighting integrals, facilitating high-quality reconstruction and relighting. A residual pass with spherical-mipmap-based directional encoding further refines the appearance modeling. Experiments demonstrate that RGS-DR achieves high-quality reconstruction and rendering quality for shiny objects, often outperforming reconstruction-exclusive state-of-the-art methods incapable of relighting.
Similar Papers
RTR-GS: 3D Gaussian Splatting for Inverse Rendering with Radiance Transfer and Reflection
Graphics
Makes shiny objects look real in computer pictures.
GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
CV and Pattern Recognition
Makes shiny objects 3D models faster.
GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels
CV and Pattern Recognition
Makes shiny objects look real in computer pictures.