Research map / 3D vision / 3D generation
MinD-3D: Reconstruct High-quality 3D objects in Human Brain
Jianxiong Gao, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng, Yanwei Fu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add feature bridge diffusion model (ablation) | MinD-3D · fMRI-Shape Core | LPIPS: 0.423 -> 0.230 | Improved |
| add feature bridge diffusion model (ablation) | MinD-3D · fMRI-Shape Core | Chamfer distance: 2.071 -> 1.742 | Improved |
| add contrastive CLIP alignment of fMRI features (ablation) | MinD-3D · fMRI-Shape Core | LPIPS: 0.319 -> 0.230 | Improved |
| add contrastive CLIP alignment of fMRI features (ablation) | MinD-3D · fMRI-Shape Core | 2-way top-1 accuracy: 0.823 -> 0.839 | Improved |
| add both diffusion and contrastive modules (ablation) | MinD-3D · fMRI-Shape Core | 2-way top-1 accuracy: 0.789 -> 0.839 | Improved |
| use MinD-3D instead of fMRI-PTE-3D baseline | fMRI-to-3D decoding · fMRI-Shape Core | Chamfer distance: 1.992 -> 1.742 | Improved |
| test on unseen participant (APT) rather than in-distribution | MinD-3D · fMRI-Shape APT | Chamfer distance: 1.742 -> 2.415 | Hurt |
| test on unseen participant and unseen classes (APACT) | MinD-3D · fMRI-Shape APACT | Chamfer distance: 1.742 -> 4.181 | Hurt |
Later papers that compared with this method
3 later accepted papers report MinD-3D as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Single-Stage fMRI-to-3D Reconstruction via Viewpoint-Aware Embedding and Hierarchical Guidance (AAAI 2026 · better on 12 of 12 shared results)
- More Natural, More Real: Object-aware Gaussian Splatting for 3D Visual Decoding from Human Brain (CVPR 2026 · better on 5 of 5 shared results)
- MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset (TPAMI 2025 · better on 10 of 10 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
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.90)
- Neuro-3D: Towards 3D Visual Decoding from EEG Signals (CVPR 2025 · similarity 0.90)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.89)
- NSD-Imagery: A Benchmark Dataset for Extending fMRI Vision Decoding Methods to Mental Imagery (CVPR 2025 · similarity 0.89)
- MindBridge: A Cross-Subject Brain Decoding Framework (CVPR 2024 · similarity 0.88)
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding (NeurIPS 2025 · similarity 0.88)
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.
