Context-Aware Multi-view Stereo Network for Efficient Edge-Preserving Depth Estimation

W Su, W Tao - International Journal of Computer Vision, 2025 - Springer
Learning-based multi-view stereo methods have achieved great progress in recent years by
employing the coarse-to-fine depth estimation framework. However, existing methods still …

Points and Patches in Textures by Exploring in Monocular Depth Estimation

D Wu, G Zhang, W Ming, W Wang… - 2024 2nd International …, 2024 - ieeexplore.ieee.org
Rich texture information is sometimes not good for deep learning, and can introduce
unwanted noise information, especially for monocular depth learning. In order to solve the …