atlas

Research map / 3D vision / 3D generation

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

AAAI 2021 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
use geometrically consistent backprojection and CT2Xray-based forward projection rather than X2CT (ablation)3DPN · Simulated radiographs, novel viewPSNR: 20.20 -> 27.22Helped
use CT2Xray material-dependent attenuation instead of DRR projection (ablation)3DPN · Simulated radiographs, novel viewPSNR: 19.79 -> 27.22Helped
use CT2Xray material-dependent attenuation instead of DRR projection (ablation)3DPN · Simulated radiographs, novel viewSSIM: 0.867 -> 0.929Mixed
add 2DRN real-radiograph refinement to 3DPN (ablation)XraySyn · Real radiographs, novel viewFID: 1.090 -> 0.319Helped
add M to 2DRN to pass input-image information through generated filter parameters (ablation)XraySyn · Real radiographs, input viewPSNR: 28.42 -> 30.33Helped
add M to 2DRN (ablation)XraySyn · Real radiographs, novel viewFID: 0.375 -> 0.319Helped
replace the 3D approach with a 2D image-to-image refiner (ablation)View synthesis · Simulated radiographs, novel viewPSNR: 27.22 -> 21.09Hurt
move synthesized view farther from the input view (ablation)3DPN · Simulated radiographsPSNR: 28.78 -> 25.37Hurt

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