works on

From the 1 of 11 linked papers with an AI index.

most citedEditable Physically-based Reflections in Raytraced Gaussian Radiance Fields

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.GRShow all

7 papers · 1 filter

cs.GR2026

Intrinsic decomposition and editing of 3D Gaussian splats

Alexandre Lanvin, Jeffrey Hu, Simon Lucas +2

Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image edit…

cs.GR2026

GRay: Ray Tracing 3D Gaussians Near the Speed of Splats

Yohan Poirier-Ginter, Jean-François Lalonde, George Drettakis

3D Gaussian Splatting (3DGS) is a popular representation for radiance field reconstruction, distinguished by the rendering speed of its rasterization-based renderer. While 3D Gauss…

cs.GR20262 cited

Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields

Yohan Poirier-Ginter, Jeffrey Hu, Jean-François Lalonde +1

Radiance fields such as 3D Gaussian Splatting allow real-time rendering of scenes captured from photos. They also reconstruct most specular reflections with high visual quality, bu…

cs.GR2026

Lighting-Consistent Object Transfer Across Radiance Fields

Nicolás Violante, George Kopanas, Linus Franke +2

3D Gaussian Splatting (3DGS) is widely used to capture and render real scenes. Compositing objects from one capture into another has applications in many domains, such as VFX, arch…

cs.GR2025

Splat and Replace: 3D Reconstruction with Repetitive Elements

Nicolás Violante, Andreas Meuleman, Alban Gauthier +3

We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthe…

cs.GR2025

Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?

Adam Celarek, George Kopanas, George Drettakis +2

Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view syn…