atlas

Research map / Point clouds / Shape and surface completion

Neural Kernel Surface Reconstruction

CVPR 2023 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 99 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use gradient-based energy fitting instead of exact positional interpolationNeural Kernel Surface Reconstruction · ABC/Thingi10K and ShapeNet reconstructionreconstruction qualityHelped
Remove the gradient-based matrices from the coefficient solve (ablation)NKSR · Ablation studyIoUHurt
Remove hierarchy levels from the linear solver (ablation)NKSR · Ablation studyIoUHurt
Increase feature dimension for kernel computation (ablation)NKSR · Ablation studyIoUHelped
Vary voxel size (ablation)NKSR · Ablation studyIoUMixed
Train one kitchen-sink model on mixed datasets instead of a domain-specific modelNKSR · ABC/Thingi10K and CARLAreconstruction qualityMixed
Use a globally supported kernel with exact positional occupancy constraintsNKF · Noisy point-cloud reconstructionnoise robustnessHurt

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