A two-stage diffusion model generates realistic depth noise on synthetic CAD data, and pretraining 3D networks on the resulting data improves few-shot real-world 3D tasks.
Unsupervised pixel- level domain adaptation with generative adversarial net- works
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion
A two-stage diffusion model generates realistic depth noise on synthetic CAD data, and pretraining 3D networks on the resulting data improves few-shot real-world 3D tasks.