Research map / Image generation / Fast diffusion sampling
BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation
Diego Garcia Cerdas, Christina Sartzetaki, Magnus Petersen, Gemma Roig, Pascal Mettes, Iris Groen
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes BrainACTIV, a diffusion-based image manipulation method that edits images to identify visuo-semantic properties driving selectivity in cortical brain regions.
Problem
Existing brain-optimized image synthesis methods generate samples independently without structural constraints, making it hard to isolate which visuo-semantic properties drive neural selectivity.
Approach
Uses diffusion-based image manipulation to make controlled, structured edits to images that are optimized to drive a target cortical population, so that the edits reveal which visuo-semantic properties cause selectivity.
Closest papers by meaning
- In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain (NeurIPS 2025 · similarity 0.91)
- NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity (NeurIPS 2026 · similarity 0.90)
- BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity (ICLR 2024 · similarity 0.89)
- Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers (ICLR 2025 · similarity 0.89)
- MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI (ICLR 2025 · similarity 0.88)
- Finding Shared Decodable Concepts and their Negations in the Brain (ICLR 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.
