Vision Foundation Models

MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement featured image

MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement

Unlocking the full potential of ViT-based stereo matching.

haoyu-zhang
All-in-One: Transferring Vision Foundation Models into Stereo Matching featured image

All-in-One: Transferring Vision Foundation Models into Stereo Matching

AIOStereo flexibly selects and transfers knowledge from multiple heterogeneous VFMs to a single stereo matching model. Rank 1st on Middlebury Stereo Evaluation.

jingyi-zhou