Depth Anything in $360^circ$: Towards Scale Invariance in the Wild

2025-12-28

AI Summary

解决360度全景深度估计在开放世界泛化能力不足问题，提出DA360方法，通过ViT骨干网络学习平移参数并整合圆形填充技术，提升模型性能。

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: State Estimation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Panoramic depth estimation provides a comprehensive solution for capturing complete $360^circ$ environmental structural information, offering significant benefits for robotics and AR/VR applications. However, while extensively studied in indoor settings, its zero-shot generalization to open-world domains lags far behind perspective images, which benefit from abundant training data. This disparity makes transferring capabilities from the perspective domain an attractive solution. To bridge this gap, we present Depth Anything in $360^circ$ (DA360), a panoramic-adapted version of Depth Anything V2. Our key innovation involves learning a shift parameter from the ViT backbone, transforming the model's scale- and shift-invariant output into a scale-invariant estimate that directly yields well-formed 3D point clouds. This is complemented by integrating circular padding into the DPT decoder to eliminate seam artifacts, ensuring spatially coherent depth maps that respect spherical continuity. Evaluated on standard indoor benchmarks and our newly curated outdoor dataset, Metropolis, DA360 shows substantial gains over its base model, achieving over 50% and 10% relative depth error reduction on indoor and outdoor benchmarks, respectively. Furthermore, DA360 significantly outperforms robust panoramic depth estimation methods, achieving about 30% relative error improvement compared to PanDA across all three test datasets and establishing new state-of-the-art performance for zero-shot panoramic depth estimation.

Problem

• Improving zero-shot generalization of panoramic depth estimation to open-world outdoor domains
• Bridging performance gap between perspective and panoramic depth estimation methods
• Eliminating seam artifacts in panoramic depth maps for spatially coherent 3D reconstruction

Innovation

• Learning shift parameter for scale-invariant depth estimation
• Integrating circular padding to eliminate seam artifacts
• Achieving state-of-the-art zero-shot panoramic depth estimation