DA360: Panoramic Depth Estimation Breakthrough
Research Paper#Computer Vision, Depth Estimation, 360-degree vision🔬 Research|Analyzed: Jan 3, 2026 16:20•
Published: Dec 28, 2025 07:12
•1 min read
•ArXivAnalysis
This paper introduces DA360, a novel approach to panoramic depth estimation that significantly improves upon existing methods, particularly in zero-shot generalization to outdoor environments. The key innovation of learning a shift parameter for scale invariance and the use of circular padding are crucial for generating accurate and spatially coherent 3D point clouds from 360-degree images. The substantial performance gains over existing methods and the creation of a new outdoor dataset (Metropolis) highlight the paper's contribution to the field.
Key Takeaways
- •DA360 is a novel panoramic depth estimation model.
- •It leverages a shift parameter for scale invariance and circular padding for spatial coherence.
- •DA360 achieves state-of-the-art performance in zero-shot panoramic depth estimation.
- •The paper introduces a new outdoor dataset, Metropolis.
Reference / Citation
View Original"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."