Depth Anything 3: DA3NESTED GIANT LARGE Model Description DA3 Nested model combining the any view Giant model with the metric Large model for metric scale visual geometry reconstruction. This is our recommended model that combines all capabilities. Property Value Model Series Nested Parameters 1.40B License CC BY NC 4.0 ⚠️ Non commercial use only due to CC BY NC 4.0 license. Capabilities ✅ Relative Depth ✅ Pose Estimation ✅ Pose Conditioning ✅ 3D Gaussians ✅ 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. ✨ 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…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy