Tag
This review reframes industrial visual sim-to-real as a domain-gap problem organized by prior availability, distinguishing CAD-guided, CAD-unavailable, and boundary-prior settings to connect CAD-based detection and 6D pose-estimation literature with industrial anomaly and surface-inspection literature.
Realiz3D introduces domain-aware learning to decouple visual domain from control signals in 3D-consistent image generation, using residual adapters and layer-specific denoising to produce photorealistic outputs from synthetic renders.