Cranio-Diff applies a conditioned diffusion model with ControlNet and text prompts to reconstruct faces from skull X-rays, evaluated on a synthesized dataset of 4320 samples from 120 subjects across age and BMI variations.
Cross-domain identity representation for skull to face matching with benchmark dataset.arXiv preprint arXiv:2507.08329, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cranio-Diff: Diffusion-based Cross-domain Craniofacial Reconstruction with 2D X-ray Skull Guidance and Structural Identity Constraints
Cranio-Diff applies a conditioned diffusion model with ControlNet and text prompts to reconstruct faces from skull X-rays, evaluated on a synthesized dataset of 4320 samples from 120 subjects across age and BMI variations.