Visual Question Answering on 360{\deg} Images

TL;DR

This paper introduces VQA 360, a new dataset and task for visual question answering on 360-degree images, highlighting the challenges and proposing models that improve spatial understanding over traditional methods.

Contribution

The paper presents the first VQA 360 dataset, analyzes models tailored for 360 images, and establishes a benchmark for future research in this area.

Findings

Cubemap-based model outperforms equirectangular models.

Significant gap remains between human and machine performance.

Proposed models effectively utilize multi-resolution spatial information.

Abstract

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.