核心概念
Proposing Elite360D for efficient 360 depth estimation with superior performance and minimal computational cost.
摘要
Recent approaches focus on cross-projection fusion for 360 depth estimation.
Elite360D inputs ERP image and ICOSAP point set for learning representation.
B2F module captures semantic- and distance-aware dependencies for accurate depth estimation.
Outperforms prior arts on benchmark datasets with minimal parameters.
Three-fold contributions: ICOSAP introduction, B2F module proposal, diverse encoder backbone support.
引述
"Our Elite360D significantly improves plain-backbones’ performance with minimal computational memory."