AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves

Shiwei Li, Yao Yao, Tian Fang, Long Quan

CVPR 2018 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 32 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
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · chairF1: 95.21 -> 95.65Improved
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · chair2F1: 74.84 -> 76.45Improved
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · fenceF1: 76.78 -> 84.09Improved
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · holderF1: 93.74 -> 93.99Improved
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · lampF1: 77.71 -> 79.41Improved
integrate reconstructed spatial curves with MVS points for surface reconstructionOurs-Curve · pylonF1: 77.61 -> 82.01Improved
optimize and extend 3D curves instead of using initial 3D line segments (ablation)Ours-Curve · six synthetic datasetsF1: 91.70 -> 95.65; 72.89 -> 76.45; 79.02 -> 84.09; 89.21 -> 93.99; 74.27 -> 79.41; 81.07 -> 82.01Improved
use curve-conformed Delaunay refinement instead of uniform point sampling in curve confidence regions (ablation)Ours-Curve · six synthetic datasetsF1: 91.87 -> 95.65; 75.25 -> 76.45; 81.68 -> 84.09; 90.63 -> 93.99; 77.42 -> 79.41; 80.51 -> 82.01Improved
integrate spatial curves rather than relying on point-based reconstructionOurs-Curve vs Vu · six synthetic datasetsaccuracyMixed

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