Preprint
Aug 2026
LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
LiteMVS is a lightweight multi-view depth estimation model that integrates plane-sweep geometric reasoning with strong monocular semantic and structural priors and employs a Mixture-of-Experts (MoE) formulation to enable adaptive geometric aggregation across depth hypotheses.
Tian-Bao Zhang, Zeyu Liu, Shuyu Wu et al.
· 0 citations