DA3-GIANT

DA3 Giant model for multi-view depth estimation, camera pose estimation, and 3D Gaussian estimation. This is the flagship 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

翻訳準備中のため原文を表示しています