1 citations · 2 across the 4 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
Tianbao Zhang, Zeyu Liu, Shuyu Wu +4
Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods primarily rely on geometric cor…
cs.CV2022★ 1 cited
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
Xinjiang Wang, Zeyu Liu, Yu Hu +3
We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints a…
cs.CV2021★ 1 cited
StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation
Boying Li, Yuan Huang, Zeyu Liu +2
Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the l…