AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Deep Hybrid Self-Prior for Full 3D Mesh Generation

Xingkui Wei, Zhengqing Chen, Yanwei Fu, Zhaopeng Cui, Yinda Zhang

ICCV 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 28 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 2D self-prior refinement on top of 3D prior (Point2Mesh as ablation without 2D prior) (ablation)3D self-prior mesh network · Synthetic 14 textured meshesF-score: 97.2 -> 97.7Improved
add 2D self-prior refinement (ablation)Point2Mesh · Thingi10K (sampled point clouds)F-score: 93.4 -> 96.1Improved
add 2D self-prior refinement (ablation)Point2Mesh · COSEG (sampled point clouds)F-score: 92.8 -> 96.2Improved
add 2D self-prior refinement (ablation)Point2Mesh · ShapeNet (sampled point clouds)F-score: 91.4 -> 95.7Improved
add 2D self-prior refinement (ablation)Point2Mesh · Synthetic 14 textured meshesChamfer distance: 0.0601 -> 0.0526Improved
hybrid prior vs Point2Mesh under 2% coordinate noise (ablation)Point2Mesh · Synthetic, input noise 2%F-score: 70.1 -> 83.5Improved
hybrid prior vs Point2Mesh under 10% coordinate noise (ablation)Point2Mesh · Synthetic, input noise 10%F-score: 18.0 -> 37.6Improved
add 2D UV-map texture network instead of MeshCNN per-vertex color (ablation)texture reconstruction · Texture quality, rendered viewsNIQE: 20.39 -> 19.35Improved
add edge length loss to 3D prior network (ablation)3D prior network · Convergence speedsteps to similar mesh quality: 4000 steps -> 1000 stepsImproved
expand UV atlas valid region by a few pixels (ablation)2D prior refinement · Mesh boundary artifactsartifact removalNo clear effect
larger Gaussian perturbation in 2D prior input (ablation)2D prior network · Qualitative outputsmoothness vs detailMixed
use distance UV map w.r.t. anchor point instead of XYZ map (ablation)2D prior network · Mesh refinementgeometry qualityHurt

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