Cranio-Diff: Diffusion-based Cross-domain Craniofacial Reconstruction with 2D X-ray Skull Guidance and Structural Identity Constraints
2026-06-08 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called Cranio-Diff to create realistic face images from X-ray pictures of skulls, which is useful in craniofacial reconstruction. Unlike earlier models, their approach better matches the structure and features between skulls and faces by combining structural guidance and biometric information. They tested their method on a unique large dataset with variations in age and body size, showing it produces higher quality images and better identification results than previous techniques. Their work could help forensic investigations by providing more accurate facial reconstructions from skulls.
craniofacial reconstructiondiffusion modelsCycleGANPix2PixX-ray imagingControlNetbiometric conditioningFIDArcFace scoreforensic investigation
Authors
Ravi Shankar Prasad, Naresh Gurjar, Shashank Baghel, Chirag, Dinesh Singh
Abstract
The state-of-the-art generative models, such as CycleGAN, Pix2Pix, and diffusion models have demonstrated remarkable performance in the face generation task. However, they fail to effectively capture cross-modality semantic information in craniofacial reconstruction when translating from the skull (x-ray) to the face (optical) domain, due to a mismatch in the alignment of structural identity across modalities. To address this issue, we propose Cranio-Diff, a diffusion-based framework for cross-domain cranio-facial reconstruction from 2D X-ray skull images. The proposed approach integrates skull-conditioned structural guidance through ControlNet with biometric text conditioning to generate a face which is more semantically and structurally aligned with the given skull. The proposed Cranio-diff method is evaluated on skull-face dataset obtained from X-ray scans of 120 subjects in lateral and frontal views. To enable controlled evaluation, each face image is synthesised across three age groups (25, 45, 65) and three BMI variations of -10%, baseline and +10%, yielding 4320 paired samples. To the best of our knowledge, this is the only X-ray-face dataset with this magnitude. Extensive experiments showed that the proposed method outperforms recent existing approaches in both generated image quality and retrieval task. Finally, to evaluate the performance of our proposed method, we have evaluated the quality of the generated image using FID, IS, SSIM, LPIPS, PSNR and ArcFace score. Additionally, retrieval performance is evaluated using recall@k, mAP@k and MRR@k. Obtained experimental results demonstrate that the proposed method can be used as an alternate tool in providing aid in forensic investigations.