Depth Anything 3: DA3METRIC LARGE noqa: E501 Model Description DA3 Metric Large model specialized for metric depth estimation in monocular settings, ideal for applications requiring real world scale. Canonical metric depth; multiplying by focal length gives metric depth. Property Value Model Series Monocular Metric Depth Parameters 0.35B License Apache 2.0 Capabilities ✅ Relative Depth ✅ Metric Depth ✅ Sky Segmentation Quick Start Installation Basic Example Command Line Interface Model Details 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 Key Insights 💎 A single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization. noqa: E501 ✨ A singular depth ray representation obviates the need for complex multi task learning. Performance 🏆 Depth Anything 3 significantly outperforms: Depth Anything 2 for monocular depth estimation VGGT for multi view depth estimation and pose estimation For detailed benchmarks, please refer to our paper. noqa: E501 Limitations The model is trained on…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy