# Visual Question Answering on 360deg Images

arXiv: https://arxiv.org/abs/2001.03339 · HTML: https://mlsanity.com/paper/2001.03339/

## Key facts

- Cited by 15 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 10 Jan 2020.

## Built on by (most cited first, 15 of 15)

- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [3D Question Answering](https://mlsanity.com/paper/2112.08359/) (2021)
- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?](https://mlsanity.com/paper/2505.11907/) (2025)
- [BERTHop: An Effective Vision-and-Language Model for Chest X-ray Disease Diagnosis](https://mlsanity.com/paper/2108.04938/) (2021)
- [RREx-BoT: Remote Referring Expressions with a Bag of Tricks](https://mlsanity.com/paper/2301.12614/) (2023)
- [Visual Question Answering: which investigated applications?](https://mlsanity.com/paper/2103.02937/) (2021)
- [Omnidirectional Spatial Modeling from Correlated Panoramas](https://mlsanity.com/paper/2509.02164/) (2025)
- [EAGOR: Embodied Reasoning in Omni-direction](https://mlsanity.com/paper/2607.06165/) (2026)
- [360deg Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method](https://mlsanity.com/paper/2603.16179/) (2026)
- [Attention in Reasoning: Dataset, Analysis, and Modeling](https://mlsanity.com/paper/2204.09774/) (2022)
- [HDR Environment Map Estimation with Latent Diffusion Models](https://mlsanity.com/paper/2507.21261/) (2025)
- [Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments](https://mlsanity.com/paper/2509.00176/) (2025)
- [Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images](https://mlsanity.com/paper/2609.33288/) (2026)
- [SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera](https://mlsanity.com/paper/2609.33462/) (2026)

## Abstract (arXiv)

In this work, we introduce VQA 360, a novel task of visual question answering on 360 images. Unlike a normal field-of-view image, a 360 image captures the entire visual content around the optical center of a camera, demanding more sophisticated spatial understanding and reasoning. To address this problem, we collect the first VQA 360 dataset, containing around 17,000 real-world image-question-answer triplets for a variety of question types. We then study two different VQA models on VQA 360, including one conventional model that takes an equirectangular image (with intrinsic distortion) as input and one dedicated model that first projects a 360 image onto cubemaps and subsequently aggregates the information from multiple spatial resolutions. We demonstrate that the cubemap-based model with multi-level fusion and attention diffusion performs favorably against other variants and the equirectangular-based models. Nevertheless, the gap between the humans' and machines' performance reveals the need for more advanced VQA 360 algorithms. We, therefore, expect our dataset and studies to serve as the benchmark for future development in this challenging task. Dataset, code, and pre-trained models are available online.