Abstract

Cranial implant generation is an important task in medical imaging. Recent point cloud based generative methods, particularly flowmatching,offerstrongreconstructionqualityandefficientsampling, but still require multiple neural function evaluations during inference. Thislimitsrapidgenerationofmultipleplausibleimplantcandidates.We proposeTeacher-guidedEndpointDistillation(TED),asimpleone-step distillationframeworkforconditionalcranialimplantgenerationonpoint clouds.TEDtrainsaone-stepstudentusingteacher-guidedendpointsupervision and geometric matching losses, while avoiding explicit path straightening.WeevaluateTEDontheSkullFixandSkullBreakbenchmarks. TED achieves the best overall performance on the SkullBreak dataset, remains competitive on SkullFix, and provides the strongest Chamfer distance performance among the compared one-step methods. In addition, TED generates implants in approximately 0.04s per sample. These results show that one-step distillation can substantially accelerate conditional point cloud implant generation without sacrificing reconstruction quality.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_017.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=O9laz2Q2Kw

BibTex

@InProceedings{KwaKam_MedPCFMTED_MICCAISAT2026,
        author = { Kwarciak, Kamil AND Wodzinski, Marek},
        title = { { MedPCFM-TED: One-Step Point Cloud Flow Matching for Implant Generation via Teacher-Guided Endpoint Distillation } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17258},
        month = {pending},
        page = {pending}
}


back to top