MedPCFM-TED: One-Step Point Cloud Flow Matching for Implant Generation via Teacher-Guided Endpoint Distillation
On the map: Diffusion models → 3D, point cloud and scene generation
Abstract (arXiv)
Cranial implant generation is an important task in medical imaging. Recent point cloud based generative methods, particularly flow matching, offer strong reconstruction quality and efficient sampling, but still require multiple neural function evaluations during inference. This limits rapid generation of multiple plausible implant candidates. We propose Teacher-guided Endpoint Distillation (TED), a simple one-step distillation framework for conditional cranial implant generation on point clouds. TED trains a one-step student using teacher-guided endpoint supervision and geometric matching losses, while avoiding explicit path straightening. We evaluate TED on the SkullFix and SkullBreak benchmarks. 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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 16 of its 23 references that are in the map. First posted on arXiv 15 Sep 2026.
Builds on
16 of 23 references.
Closest ancestors · 4
Same direction, newest first
- 2026MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching23 Jun
- 2023Point Cloud Diffusion Models for Automatic Implant Generation14 Mar
- 2022Fast Point Cloud Generation with Straight Flows4 Dec
- 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar
Other references · 12
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
- 2020Convolutional Occupancy Networkscited by 761
- 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
- 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
- 2024Flow Matching Guide and Codecited by 301
- 2021Shape As Points: A Differentiable Poisson Solvercited by 187
- 2025MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillationcited by 31
- 2022Deep Learning-based Framework for Automatic Cranial Defect Reconstruction and Implant Modelingcited by 8
- 2023High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformerscited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025MFM-point: Multi-scale Flow Matching for Point Cloud Generation
- 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
- 2024Improving Deep Learning-based Automatic Cranial Defect Reconstruction by Heavy Data Augmentation: From Image Registration to Latent Diffusion Models
- 2026BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
- 2026Cranio-Diff: Diffusion-based Cross-domain Craniofacial Reconstruction with 2D X-ray Skull Guidance and Structural Identity Constraints
- 2025Flow Matching for Conditional MRI-CT and CBCT-CT Image Synthesis
- 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
- 2022Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape Model