DA3-LARGE

DA3 Large model for multi-view depth estimation and camera pose estimation. Foundation model with unified depth-ray representation. - **Developed by:** ByteDance Seed Team - **Model Type:** Vision Transformer for Visual Geometry - **Architecture:** Plain transformer with unified depth-ray representation - **Training Data:** Public academic datasets only 💎 A **single plain transformer** (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization. # noqa: E501

번역 준비 중입니다. 원문을 표시합니다.