Research map / 3D vision / Face and shape
Drawing Developmental Trajectory from Cortical Surface Reconstruction
Wenxuan Wu, Ruowen Qu, Zhongliang Liu, Zhuoyan Dai, Dongzi Shi, Sijin Yu, Tong Xiong, Shiping Liu, Xiangmin Xu, Xiaofen Xing, Xin Zhang
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 ACDE with adaptive steps over fixed-step baseline (ablation) | white matter reconstruction · dHCP white matter | ASSD (mm): 0.112 -> 0.115 | No clear effect |
| add single-time-point data to multi-time-point training (ablation) | ACDE · dHCP white matter | ASSD (mm): 0.338 -> 0.115 | Improved |
| add multi-time-point paired training to ST-only ACDE (ablation) | ACDE · dHCP sulcal depth | development trajectory | Improved |
| replace Resampling with PCIL curriculum (ablation) | ACDE · dHCP sulcal depth | MAE: 0.782 -> 0.502 | Improved |
| replace Resampling with PCIL curriculum (ablation) | ACDE · dHCP white matter | ASSD (mm): 0.191 -> 0.137 | Improved |
| add knowledge distillation after PCIL (ablation) | ACDE · dHCP sulcal depth | MAE: 0.502 -> 0.451 | Improved |
| add knowledge distillation after PCIL (ablation) | ACDE · dHCP white matter | ASSD (mm): 0.137 -> 0.109 | Improved |
| add global thickness loss Lg (ablation) | pial dual-task · dHCP cortical thickness | MAE: 0.482 -> 0.327 | Improved |
| add consistency loss Lc (ablation) | pial dual-task · dHCP cortical thickness | MAE: 0.482 -> 0.199 | Improved |
| add Lg on top of Lc (ablation) | pial dual-task · dHCP cortical thickness | PCC: 0.819 -> 0.866 | Improved |
| use proposed method instead of S-UNet | ACDE · dHCP paired test: sulcal depth | MAE: 0.532 -> 0.451 | Improved |
| use proposed method instead of CoTAN | ACDE · dHCP white matter | ASSD (mm): 0.112 -> 0.109 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Corticalflow — CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction (NeurIPS 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation (NeurIPS 2023 · similarity 0.88)
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction (ICLR 2024 · similarity 0.85)
- Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals (NeurIPS 2024 · similarity 0.83)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.83)
- Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry (NeurIPS 2025 · similarity 0.83)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 2025 · similarity 0.82)
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.
