A splatting-free path-traced inverse rendering method for 3D Gaussian fields that defines a path-space interaction model enabling unbiased Monte-Carlo rendering and optimization under the full rendering equation with multi-bounce transport.
Deep graph learning for spatially-varying indoor lighting prediction , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Path-Traced Inverse Rendering with Global Illumination in 3D Gaussian Fields
A splatting-free path-traced inverse rendering method for 3D Gaussian fields that defines a path-space interaction model enabling unbiased Monte-Carlo rendering and optimization under the full rendering equation with multi-bounce transport.