Presentation

<
EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing
SessionInverse Rendering
DescriptionEAG-PT reconstructs indoor scenes with 2D Gaussians for editable diffuse global illumination. By separating emissive and non-emissive components and combining efficient reconstruction with path tracing, it enables more natural, physically consistent scene editing than radiance-field methods, while avoiding the geometry limitations of mesh-based inverse rendering.
Authors
Xijie Yang
Zhejiang University
Shanghai Artificial Intelligence Laboratory
Mulin Yu
Shanghai Artificial Intelligence Laboratory
Changjian Jiang
Zhejiang University
Kerui Ren
Shanghai Jiao Tong University
Shanghai Artificial Intelligence Laboratory
Tao Lu
Shanghai Artificial Intelligence Laboratory
Jiangmiao Pang
Shanghai Artificial Intelligence Laboratory
Dahua Lin
The Chinese University of Hong Kong
Shanghai Artificial Intelligence Laboratory
Bo Dai
The University of Hong Kong
Feeling AI
Linning Xu
The Chinese University of Hong Kong
Shanghai Artificial Intelligence Laboratory
Event Type
Technical Paper
TimeThursday, 23 July 20269:20am - 9:30am PDT
LocationRoom 408 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20269:00am - 10:30am PDTRoom 408 A
Keywords
Lighting
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationRadiance Caching for Differentiable Path Tracing
Similar Presentations
Multi-feature Radiance Baking Neural Networks for Instant Volumetric Rendering
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
Radiance Caching for Differentiable Path Tracing