CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
A 3D latent diffusion model for chest CT generation that achieves high-fidelity results while enabling control over clinical attributes through metadata conditioning and reinforcem…
Hugging Face · Daily Papers
·Max Van Puyvelde, Halil Ibrahim Gulluk
·
·▲ 1 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
- 1 upvotes da comunidade
- Temas: latent diffusion model, 3D variational autoencoder, rectified-flow transformer, adaptive layer normalization, tri-planar Frechet distance, FID
Resumo
Resumo original (em inglês), extraído do paper:
A 3D latent diffusion model for chest CT generation that achieves high-fidelity results while enabling control over clinical attributes through metadata conditioning and reinforcement learning refinement.Onde ler
// relacionados
