AI Paper Atlas

Research map / 3D vision / Face and shape

MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset

Jianxiong Gao, Yanwei Fu, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng

TPAMI 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 10 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 contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)10-way accuracy: 0.463 -> 0.616Improved
add contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)LPIPS: 0.296 -> 0.234Improved
add image branch to contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)10-way accuracy: 0.549 -> 0.616Improved
add text branch to contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)10-way accuracy: 0.563 -> 0.616Improved
add image branch to contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)PSNR: 15.79 -> 16.44Improved
add text branch to contrastive loss (ablation)MinD-3D++ · fMRI-Shape (Core set)SSIM: 0.734 -> 0.763Improved
apply contrastive loss at intermediate layer instead of final 12th layer (ablation)MinD-3D++ · fMRI-Shape (Core set)10-way accuracy: 0.604 -> 0.616Improved
apply contrastive loss at intermediate layer instead of final 12th layer (ablation)MinD-3D++ · fMRI-Shape (Core set)SSIM: 0.759 -> 0.763Improved
replace MinD-3D with MinD-3D++ (texture-aware)MinD-3D · fMRI-Shape (Core set)LPIPS: 0.306 -> 0.234Improved
replace MinD-3D with MinD-3D++ on larger datasetMinD-3D · fMRI-Objaverse10-way accuracy: 0.427 -> 0.618Improved
replace MinD-3D with MinD-3D++ in across-person and across-class testMinD-3D · fMRI-Shape APACFPD: 5.689 -> 5.347Improved
replace MinD-3D with MinD-3D++ in across-person testMinD-3D · fMRI-Shape APFPD: 3.838 -> 3.582Improved

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