AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization

Xianghui Yang, Guosheng Lin, Zhenghao Chen, Luping Zhou

TPAMI 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 6 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 hard codebook (ablation)NVF (ultra) · ShapeNet non-watertight (base classes)Normal error: 0.196 -> 0.162Improved
add hard codebook (ablation)NVF (ultra) · ShapeNet non-watertight (novel classes)Normal error: 0.193 -> 0.169Improved
replace hard codebook with soft codebook (ablation)NVF (ultra) · ShapeNet non-watertight (base classes)Normal error: 0.162 -> 0.143Improved
replace hard codebook with soft codebook (ablation)NVF (ultra) · ShapeNet non-watertight (novel classes)Normal error: 0.169 -> 0.153Improved
add curl regularization to soft codebook (ablation)NVF (ultra) · ShapeNet non-watertight (base classes)Normal error: 0.143 -> 0.144No clear effect
add curl regularization to soft codebook (ablation)NVF (ultra) · ShapeNet non-watertight (novel classes)Chamfer distance: 0.818 -> 0.841Hurt
add direction loss to soft codebook plus curl (ablation)NVF (ultra) · ShapeNet non-watertight (base classes)Normal error: 0.144 -> 0.137Improved
add direction loss to soft codebook plus curl (ablation)NVF (ultra) · ShapeNet non-watertight (novel classes)Chamfer distance: 0.841 -> 0.745Improved
use PointTransformer backbone instead of 3D convolution (ablation)NVF (ultra) · ShapeNet non-watertight (base classes)Chamfer distance: 0.886 -> 0.810Improved
use PointTransformer backbone instead of 3D convolution (ablation)Ours (lite) · ShapeNet non-watertight (base classes)Chamfer distance: 0.92 -> 0.85Improved
use soft codebook with curl and direction loss (ultra) instead of hard codebook (lite)NVF · MGN (cross-domain)Chamfer distance: 0.141 -> 0.133Improved
use NVF (lite) instead of NDF for inferenceNVF · 50k-query inferenceruntime: 0.327s -> 0.113sImproved

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