SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Posheng, Cheng, Powen, Faure, Gueter Josmy, Su, Hung-Ting, Hsu, Winston H.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909043365249024
author Chen, Posheng
Cheng, Powen
Faure, Gueter Josmy
Su, Hung-Ting
Hsu, Winston H.
author_facet Chen, Posheng
Cheng, Powen
Faure, Gueter Josmy
Su, Hung-Ting
Hsu, Winston H.
contents In real-world scenes, target objects may reside in regions that are not visible. While humans can often infer the locations of occluded objects from context and commonsense knowledge, this capability remains a major challenge for vision-language models (VLMs). To address this gap, we introduce SceneFunRI, a benchmark for Reasoning the Invisible. Based on the SceneFun3D dataset, SceneFunRI formulates the task as a 2D spatial reasoning problem via a semi-automatic pipeline and comprises 855 instances. It requires models to infer the locations of invisible functional objects from task instructions and commonsense reasoning. The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. We group our prompting analysis into three categories: Strong Instruction Prompting, Reasoning-based Prompting, and Spatial Process of Elimination (SPoE). These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs, motivating future work on models that more tightly integrate task intent, commonsense priors, spatial grounding, and uncertainty-aware search.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14704
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization
Chen, Posheng
Cheng, Powen
Faure, Gueter Josmy
Su, Hung-Ting
Hsu, Winston H.
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
In real-world scenes, target objects may reside in regions that are not visible. While humans can often infer the locations of occluded objects from context and commonsense knowledge, this capability remains a major challenge for vision-language models (VLMs). To address this gap, we introduce SceneFunRI, a benchmark for Reasoning the Invisible. Based on the SceneFun3D dataset, SceneFunRI formulates the task as a 2D spatial reasoning problem via a semi-automatic pipeline and comprises 855 instances. It requires models to infer the locations of invisible functional objects from task instructions and commonsense reasoning. The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. We group our prompting analysis into three categories: Strong Instruction Prompting, Reasoning-based Prompting, and Spatial Process of Elimination (SPoE). These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs, motivating future work on models that more tightly integrate task intent, commonsense priors, spatial grounding, and uncertainty-aware search.
title SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2605.14704