1 code implementation • 11 May 2024 • Zhen Tan, Zongtan Zhou, Yangbing Ge, Zi Wang, Xieyuanli Chen, Dewen Hu
Our approach explicitly utilizes monocular depth priors through three key advancements: 1) we propose a novel depth-based ray sampling strategy based on the truncated normal distribution, which improves the convergence speed and accuracy of pose estimation; 2) to circumvent local minima and refine depth geometry, we introduce a coarse-to-fine training strategy that progressively improves the depth precision; 3) we propose a more robust inter-frame point constraint that enhances robustness against depth noise during training.