构建新数据集与模型，更准确评估3D图像观感体验。
What Makes for a Good Stereoscopic Image?
- 构建含真实与合成3D图像的偏好标注数据集SCOPE。
- 新模型iSQoE在立体转换对比中更贴近用户偏好。
- 跨头戴设备用户偏好高度一致，适合VR内容优化。
随着虚拟现实（VR）头显的快速发展，有效衡量立体视觉体验质量（SQoE）对提供沉浸式且舒适的3D体验至关重要。然而，现有立体质量度量方法多聚焦于视觉不适或图像质量等单一方面，且长期受数据限制。为此，我们提出SCOPE（Stereoscopic COntent Preference Evaluation）数据集，包含大量具有常见感知失真和伪影的真实与合成立体图像。该数据集通过在VR头显上收集偏好标注，发现用户偏好在不同头显间具有显著一致性。此外，我们提出了iSQoE模型，基于该数据集训练，用于立体质量体验评估。实验表明，iSQoE在比较单目转立体方法时，其预测结果比现有方法更符合人类偏好。
原文摘要 · Abstract (English)
With rapid advancements in virtual reality (VR) headsets, effectively measuring stereoscopic quality of experience (SQoE) has become essential for delivering immersive and comfortable 3D experiences. However, most existing stereo metrics focus on isolated aspects of the viewing experience such as visual discomfort or image quality, and have traditionally faced data limitations. To address these gaps, we present SCOPE (Stereoscopic COntent Preference Evaluation), a new dataset comprised of real and synthetic stereoscopic images featuring a wide range of common perceptual distortions and artifacts. The dataset is labeled with preference annotations collected on a VR headset, with our findings indicating a notable degree of consistency in user preferences across different headsets. Additionally, we present iSQoE, a new model for stereo quality of experience assessment trained on our dataset. We show that iSQoE aligns better with human preferences than existing methods when comparing mono-to-stereo conversion methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。