AI is happening. The future is updating.DA3-LARGE-1.1
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 π A **single plain transformer** (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization. # noqa: E501
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 π A **single plain transformer** (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization. # noqa: E501