Research map / Label-efficient and robust learning / Recognition and long-tail
Neural Photofit: Gaze-Based Mental Image Reconstruction
Florian Strohm, Ekta Sood, Sven Mayer, Philipp Müller, Mihai Bâce, Andreas Bulling
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 |
|---|---|---|---|
| use one-second fixation maps (30) instead of five-second maps (6) (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | accuracy (All): 56.8% -> 61.9% | Improved |
| use one-second fixation maps (30) instead of five-second maps (6) (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | MASD (All): 25.15 -> 23.37 | Improved |
| use multiple fixation maps over time instead of one 30 s map (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | accuracy (All): 57.9% -> 61.9% | Improved |
| use multiple fixation maps over time instead of one 30 s map (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | MASD (All): 23.96 -> 23.37 | Improved |
| use multiple fixation maps over time instead of one 30 s map (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set (nose features) | accuracy: 54.7% -> 45.3% | Hurt |
| add attention mechanism to scoring network (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | accuracy (All): 52.2% -> 61.9% | Improved |
| add attention mechanism to scoring network (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set | MASD (All): 26.35 -> 23.37 | Improved |
| add attention mechanism to scoring network (ablation) | Neural Photofit · Synthetic FaceMaker faces, test set (eyes features) | accuracy: 56.8% -> 77.0% | Improved |
| use gaze-based scoring network instead of mean of auxiliary faces | Neural Photofit · Synthetic FaceMaker faces, test set | MASD (All): 30.26 -> 23.37 | Improved |
| use gaze-based scoring network instead of random feature selection | Neural Photofit · Synthetic FaceMaker faces, test set | accuracy (All): 16.7% -> 61.9% | Improved |
| use Neural Photofit reconstruction instead of baseline in human preference | Neural Photofit · User study | preference rate: 50% -> 79% | Improved |
Closest papers by meaning
- Mind Artist: Creating Artistic Snapshots with Human Thought (CVPR 2024 · similarity 0.89)
- $i$MIND: Insightful Multi-subject Invariant Neural Decoding (NeurIPS 2025 · similarity 0.87)
- NSD-Imagery: A Benchmark Dataset for Extending fMRI Vision Decoding Methods to Mental Imagery (CVPR 2025 · similarity 0.87)
- Sharingan: A Transformer Architecture for Multi-Person Gaze Following (CVPR 2024 · similarity 0.86)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.86)
- Toward Generalizing Visual Brain Decoding to Unseen Subjects (ICLR 2025 · similarity 0.85)
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.
