Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations
This addresses the labor-intensive data annotation challenge in panoramic layout estimation, though it appears incremental as it builds on existing semi-supervised approaches.
The paper tackles the problem of reducing reliance on expensive annotated data for 360-degree layout estimation by proposing a semi-supervised method that uses panoramic-specific perturbations, achieving significant advantages over state-of-the-art solutions on three benchmarks.
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.