R3D2 trains a lightweight diffusion model on synthetic placements of 3DGS-generated assets to produce photorealistic insertions with consistent illumination into autonomous driving scenes.
Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
R3D2 trains a lightweight diffusion model on synthetic placements of 3DGS-generated assets to produce photorealistic insertions with consistent illumination into autonomous driving scenes.