Abstract
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Shen, Z., Lin, C., Zheng, S., Li, F., Cong, R., Bai, H., & Zhao, Y. (2026). Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation. https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation
MLA 9
Shen, Zhijie, et al. "Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation." https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation.
Chicago (author–date)
Shen, Zhijie, Chunyu Lin, Shuai Zheng, Feng Li, Runmin Cong, Huihui Bai, and Yao Zhao. 2026. "Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation." https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation.
Harvard
Shen, Z., Lin, C., Zheng, S., Li, F., Cong, R., Bai, H. and Zhao, Y. (2026) 'Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation', Available at: https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation.
Vancouver
Shen Z, Lin C, Zheng S, Li F, Cong R, Bai H, et al. Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation. https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation
IEEE
Z. Shen, C. Lin, S. Zheng, F. Li, R. Cong, H. Bai, and Y. Zhao, "Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation," https://omanscience.com/en/articles/decoupling-spherical-reasoning-from-dense-prediction-for-360-depth-estimation.