AI Paper Atlas

Research map / Point clouds / Shape and surface completion

4D Myocardium Reconstruction with Decoupled Motion and Shape Model

Xiaohan Yuan, Cong Liu, Yangang Wang

ICCV 2023 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 14 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
decouple motion code from shape code (versus DeepSDF/DIT/DIF with coupled codes)4D myocardium reconstruction · Proposed dataset (SAX+LAX)EMD: 6.010 -> 3.603 (vs DIF)Improved
use ours instead of DIF with SAX-only input4D myocardium reconstruction · Proposed dataset (SAX)Chamfer Distance: 2.891 -> 2.634Improved
add long-axis (LAX) contours to short-axis input for our methodOurs · Proposed datasetEMD: 6.173 -> 3.603Improved
add LAX contours to input for baseline methodsDeepSDF and DIF · Proposed datasetChamfer Distance: DIF 2.891 -> 2.858; DeepSDF 3.331 -> 2.852No clear effect
pre-train ED shape model in ED-space then train jointly with motion model (ablation)ED shape model · training loss curveloss convergenceImproved
apply method to ACDC 2017 (diseased hearts) despite training only on healthy subjectsOurs · ACDC 2017Dice: 0.702 -> 0.765 (vs DIT)Improved

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