AI Paper Atlas

Research map / 3D vision / Face and shape

NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing

Bangbang Yang, Chong Bao, Junyi Zeng, Hujun Bao, Yinda Zhang, Zhaopeng Cui, Guofeng Zhang

ECCV 2022 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 143 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 learnable sign indicators on vertices (ablation)NeuMesh · DTU Scan 69PSNR: 26.633 -> 27.254Improved
add learnable sign indicators on vertices (ablation)NeuMesh · NeRF Synthetic LegoPSNR: 27.631 -> 27.881Improved
add fine-tuning stage to distillation (ablation)NeuMesh · NeRF Synthetic LegoPSNR: 25.606 -> 27.881Improved
add fine-tuning stage to distillation (ablation)NeuMesh · DTU Scan 69LPIPS: 0.144 -> 0.113Improved
add distillation to fine-tuning (ablation)NeuMesh · NeRF Synthetic LegoPSNR: 23.583 -> 27.881Improved
add distillation to fine-tuning (ablation)NeuMesh · DTU Scan 69PSNR: 26.258 -> 27.254Improved
add learnable signed distance (ablation)NeuMesh · DTU Scan 69PSNR: 23.622 -> 27.254Improved
add learnable signed distance (ablation)NeuMesh · NeRF Synthetic LegoPSNR: 20.827 -> 27.881Improved
use mesh-based representation instead of uniform grid (ablation)NeuMesh · NeRF Synthetic LegoPSNR: 25.866 -> 27.881Improved
use mesh-based representation instead of uniform grid (ablation)NeuMesh · DTU Scan 69PSNR: 26.931 -> 27.254Improved
use full position encoding instead of relative position (ablation)NeuMesh · DTU Scan 69PSNR: 26.308 -> 27.254Improved
use mesh-based method instead of NeuSNeuMesh · DTUPSNR: 26.352 -> 28.289Improved

Later papers that compared with this method

3 later accepted papers report NeuMesh as a baseline in their results tables; 3 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