[CVPR 2024] UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model

PixelRNN | CVPR 2024Подробнее

3rd Monocular Depth Estimation Challenge CVPR 2024Подробнее

Segment Anything 2 (SAM 2): Meta AI's Newest Model | Community Q&A (Jul 30)Подробнее

CVPR 2024 Paper Compilation - TUM Visual Computing Lab & CollaboratorsПодробнее

Segment Anything Model (SAM) Breakdown | Computer Vision BreakthroughПодробнее

Segment Anything 2 (SAM 2): how to start + limitationsПодробнее