Abstract
Embodied Question Answering (EQA) requires agents to answer natural language questions about surrounding environments from visual observations. In this work, we focus on open-vocabulary episodic-memory EQA (EM-EQA), where an agent answers free-form questions using recorded observation histories. Omnidirectional images are promising for this task, as they provide wide field-of-view observations that can capture surrounding context without requiring explicit camera rotations. However, omnidirectional images introduce two challenges for EQA: (i) equirectangular projection causes severe geometric distortion that degrades vision-language model (VLM) recognition accuracy, and (ii) feeding equirectangular images directly into VLMs introduces excessive irrelevant background information, reducing answer accuracy and increasing the visual-token burden. To address these challenges, we propose a viewpoint selection method for EM-EQA using omnidirectional images. Our method converts equirectangular observations into perspective views via cubemap projection, estimates question-conditioned relevance with fine-tuned BLIP-2, and selects informative and diverse viewpoints through diversity-aware greedy selection. Experiments on the Habitat-Matterport 3D (HM3D) subset of OpenEQA show that our method achieves state-of-the-art model performance among the reported model results with equirectangular observations. Moreover, after removing rotation views, which reduces observation frames by 65.5%, our method largely maintains its answer accuracy.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kitamura, K., & Kanezaki, A. (2026). Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images. https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images
MLA 9
Kitamura, Kaname, and Asako Kanezaki. "Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images." https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images.
Chicago (author–date)
Kitamura, Kaname, and Asako Kanezaki. 2026. "Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images." https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images.
Harvard
Kitamura, K. and Kanezaki, A. (2026) 'Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images', Available at: https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images.
Vancouver
Kitamura K, Kanezaki A. Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images. https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images
IEEE
K. Kitamura, and A. Kanezaki, "Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images," https://omanscience.com/en/articles/informative-viewpoint-selection-for-episodic-memory-embodied-question-answering-using-omnidirectional-images.