AI Paper Atlas

Research map / 3D vision / 3D generation

DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays

Xuhui Liu, Zhi Qiao, Runkun Liu, Hong Li, Xiantong Zhen, Zhen Qian, Juan Zhang, Baochang Zhang

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace simple 2D-encoder conditioning with the implicit conditioning mechanism (tri-plane generator + implicit decoder) (ablation)3D conditional diffusion model · LumbarVPSNR: 29.37 -> 34.32Improved
add geometry projection loss (ablation)DiffuX2CT · LumbarVPSNR: 33.62 -> 34.32Improved
add geometry projection loss (ablation)DiffuX2CT · LumbarVFID: 16.22 -> 13.23Improved
add view modulators to fuse uw and vw planes (ablation)Tri-plane decoupling generator · LumbarVPSNR: 32.09 -> 34.32Improved
add view modulators instead of a ResNet block for plane fusion (ablation)Tri-plane decoupling generator · LumbarVPSNR: 33.07 -> 34.32Improved
add learnable uv embedding with Gaussian perturbation (ablation)Tri-plane decoupling generator · LumbarVPSNR: 34.19 -> 34.32Improved
use diffusion with ICM instead of regression ICM-Reg for downstream segmentationDiffuX2CT · CTPelvic1K 3D segmentationaverage DSC: 47.59 -> 74.10Improved
use 3D diffusion model instead of regression and GAN baselinesDiffuX2CT · CTSpine1KFID: 50.63 -> 8.90Improved
DiffuX2CT vs regression X-CTRSNet on LIDC-IDRI PSNR3DDiffuX2CT · LIDC-IDRIPSNR3D: 22.35 -> 21.15Hurt
DiffuX2CT vs X2CT-GAN on LumbarV PSNRDiffuX2CT · LumbarVPSNR: 34.27 -> 34.32No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy