AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Modeling the Vividness of Imagined Natural Scenes Reveals a Model-Common Image-Level Component in Vision Models

Morteza Mahdiani, Catherine Landry, Jasper JF van den Bosch, Frédéric Gosselin, Ian Charest

NeurIPS 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning

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.

Collected over 229,000 vividness judgments for 73,000 Natural Scenes Dataset images from 1,991 online participants and models mental image vividness using vision model features.

Problem

The visual features that support vivid mental imagery remain poorly understood.

Approach

Large-scale behavioral collection of vividness ratings for imagined natural scenes, used to model which image-level features (from vision models) predict vividness and to identify a component shared across models.

Key results

Experimental setup

Datasets: Natural Scenes Dataset

Builds on: Natural Scenes Dataset

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