AI Paper Atlas

Research map / Point clouds / Shape and surface completion

FlexPara: Flexible Neural Surface Parameterization

Yuming Zhao, Qijian Zhang, Junhui Hou, Jiazhi Xia, Wenping Wang, Ying He

TPAMI 2025 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 4 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
add differential distortion loss (DDL) (ablation)FlexPara global · Giraffeconformal distortion: 0.424 -> 0.071Improved
add triangle distortion loss (TDL) (ablation)FlexPara global · Giraffeconformal distortion: 0.088 -> 0.071Improved
add bottom 3D-2D-3D branch (ablation)FlexPara global · Giraffeconformal distortion: 0.209 -> 0.071Improved
add upper 2D-3D-2D branch (ablation)FlexPara global · Giraffeconformal distortion: 0.075 -> 0.071Improved
add bi-directional branches to multi-chart framework (ablation)FlexPara multi-chart · Beartraining time (hours): 0.34 -> 1.53Hurt
add DDL-style multi-loss to multi-chart framework (ablation)FlexPara multi-chart · Beartraining time (hours): 0.34 -> 8.95Hurt
add bi-directional branches to multi-chart framework (ablation)FlexPara multi-chart · Fishisometric distortion x1e-4: 21.4 -> 52.3Mixed
use FlexPara instead of OptCutsglobal parameterization · Torus-knotconformality error: 0.7320 -> 0.0150Improved
use FlexPara instead of Nuvomulti-chart parameterization · Bunnyisometric distortion x1e-4: 59.6 -> 6.4Improved
use FlexPara instead of FBCP-PCpoint cloud global parameterization · Spiral-ptsconformality error: 0.023 -> 0.098Hurt
switch GPU from RTX3090 to H800FlexPara · runtime scalabilityefficiency: about 75%Improved
switch GPU from RTX3090 to RTX5090FlexPara · runtime scalabilityefficiency: approximately 20%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.

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

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