AI Paper Atlas

Research map / 3D vision / Face and shape

Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

Yuxuan Wang, Xuanyu Yi, Haohan Weng, Qingshan Xu, Xiaokang Wei, Xianghui Yang, Chunchao Guo, Long Chen, Hanwang Zhang

ICCV 2025 · 3D vision › Face and shape · approach: Textured mesh generation · 18 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 Nautilus Shell representation to coordinate compression (ablation)Nautilus tokenization · Quantitative ablationChamfer distance: 0.151 -> 0.100Improved
add Nautilus Shell representation to coordinate compression (ablation)Nautilus tokenization · Quantitative ablationHausdorff distance: 0.355 -> 0.213Improved
add coordinate compression to Nautilus Shell representation (ablation)Nautilus tokenization · Quantitative ablationChamfer distance: 0.100 -> 0.092Improved
add coordinate compression to shell representation (ablation)Nautilus tokenization · Tokenization ablationCompression ratio: 0.484 -> 0.275Improved
add Nautilus Shell representation to coordinate compression (ablation)Nautilus tokenization · Tokenization ablationCompression ratio: 0.549 -> 0.275Improved
add local point encoder (PointConv) to the dual-stream conditioner (ablation)Nautilus · Quantitative ablationChamfer distance: 0.092 -> 0.087Improved
add local point encoder to the conditioner (ablation)Nautilus · Quantitative ablationHausdorff distance: 0.186 -> 0.176Improved
use Nautilus tokenization instead of AMT (ablation)mesh tokenization · Tokenization comparisonLocal ratio: 0.378 -> 0.554Improved
use Nautilus tokenization instead of EdgeRunner (ablation)mesh tokenization · Tokenization comparisonCompression ratio: 0.474 -> 0.275Improved
use Nautilus instead of MeshAnythingV2 (ablation)point-cloud mesh generation · Topological qualityManifold meshes: 29.0% -> 83.6%Improved

Later papers that compared with this method

1 later accepted paper reports Nautilus as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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