Research map / 3D vision / Human pose estimation
EchoPOSE: 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D Shape Reconstruction
Lucas Iijima, Yihao Luo, Dario Sesia, Amit Kaura, Jamil Mayet, Choon Hwai Yap
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add local transformer (TL) (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 68.20 -> 77.08 | Improved |
| add global transformer (TG) to local transformer (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 77.08 -> 84.32 | Improved |
| add geometric intersection loss (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 84.32 -> 87.52 | Improved |
| add geometric prior (initial standard affine AS) (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 85.94 -> 87.52 | Improved |
| use GHD reconstruction instead of OReX with marching cubes (ablation) | EchoPOSE poses · MITEA test | 3D Dice (%): 69.27 -> 87.52 | Improved |
| apply EchoPOSE pose correction to assumed standard poses before GHD | GHD reconstruction · MITEA test | EF error (%): 13.36 -> 1.44 | Improved |
| add third apical view A3C to A4C and A2C (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 76.00 -> 85.73 | Improved |
| add short-axis apical view SAXA (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 85.73 -> 85.77 | No clear effect |
| add short-axis basal view SAXB (ablation) | EchoPOSE · MITEA test | 3D Dice (%): 85.77 -> 87.52 | Improved |
| use nnU-Net AI segmentations instead of ideal sliced masks | EchoPOSE + GHD · MITEA vs MITEA+AI | 3D Dice (%): 87.52 -> 83.82 | Hurt |
| EchoPOSE + GHD instead of Simpson's biplane on real clinical TTE | LV quantification · Routine TTE | LV volume error (%): 17.15 -> 4.22 | Improved |
Closest papers by meaning
- EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function (NeurIPS 2026 · similarity 0.87)
- EchoONE: Segmenting Multiple Echocardiography Planes in One Model (CVPR 2025 · similarity 0.84)
- EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance (CVPR 2025 · similarity 0.83)
- Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation (NeurIPS 2025 · similarity 0.83)
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations (NeurIPS 2025 · similarity 0.83)
- Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression (CVPR 2025 · similarity 0.83)
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.
