用全景特性设计新方法，减少标注依赖，提升360布局估计精度。
Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations
- 基于全景布局和畸变先验设计协同扰动策略。
- 在三个主流数据集上超越现有最优方法，显著提升精度。
- 适合需要低标注成本的全景图像理解研究者。
现有监督式布局估计方法严重依赖高质量标注数据，而大规模高质量数据集的构建仍耗时耗力。为此，半监督方法通过使未标注数据在不同扰动下保持一致结果，降低对人工标注的依赖。然而，现有方案仅使用基础扰动，忽视了全景布局估计的独特性。本文提出新型半监督方法SemiLayout360，融合全景布局先验与畸变先验，通过全景协同扰动增强模型对潜在布局边界和畸变的感知能力。为避免剧烈扰动影响模型收敛，我们设计分组重组机制以确保先验引导的扰动有效性。在三个主流基准上的实验表明，该方法显著优于当前最优（SoTA）方案。
原文摘要 · Abstract (English)
The performance of existing supervised layout estimation methods heavily relies on the quality of data annotations. However, obtaining large-scale and high-quality datasets remains a laborious and time-consuming challenge. To solve this problem, semi-supervised approaches are introduced to relieve the demand for expensive data annotations by encouraging the consistent results of unlabeled data with different perturbations. However, existing solutions merely employ vanilla perturbations, ignoring the characteristics of panoramic layout estimation. In contrast, we propose a novel semi-supervised method named SemiLayout360, which incorporates the priors of the panoramic layout and distortion through collaborative perturbations. Specifically, we leverage the panoramic layout prior to enhance the model's focus on potential layout boundaries. Meanwhile, we introduce the panoramic distortion prior to strengthen distortion awareness. Furthermore, to prevent intense perturbations from hindering model convergence and ensure the effectiveness of prior-based perturbations, we divide and reorganize them as panoramic collaborative perturbations. Our experimental results on three mainstream benchmarks demonstrate that the proposed method offers significant advantages over existing state-of-the-art (SoTA) solutions.
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。