| Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data | ✓ Link | 0.981 | 0.043 | Depth Anything (ViT-L) | 2024-01-19 |
| Vision as Unified Multimodal Generation | ✓ Link | 0.981 | 0.04 | SenseNova-Vision | 2026-07-07 |
| DINOv3 | ✓ Link | 0.98 | 0.043 | DINOv3 + Depth Anything V2 | 2025-08-13 |
| Depth Anything 3: Recovering the Visual Space from Any Views | ✓ Link | 0.980 | | Depth Anything 3 Mono | 2025-11-13 |
| In Pursuit of Pixel Supervision for Visual Pre-training | ✓ Link | 0.980 | | Pixio-H + DPT | 2025-12-17 |
| Depth Anything V2 | ✓ Link | 0.979 | 0.044 | Depth Anything V2 (ViT-G) | 2024-06-13 |
| Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model | ✓ Link | 0.976 | 0.041 | Lotus-2 (zero-shot) | 2025-11-30 |
| Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction | ✓ Link | 0.972 | 0.051 | Lotus-D (zero-shot) | 2024-09-26 |
| CH3Depth: Efficient and Flexible Depth Foundation Model with Flow Matching | | 0.972 | 0.05 | CH3Depth (96K) | 2025-06-11 |
| DepthART: Scaling Foundation Monocular Depth to Tiny Models | ✓ Link | 0.971 | 0.053 | DepthART-L (zero-shot) | 2026-07-19 |
| AnyDepth: Depth Estimation Made Easy | ✓ Link | 0.968 | 0.06 | AnyDepth ViT-L | 2026-01-06 |
| Video Generative Models as Geometry Learner | ✓ Link | 0.968 | 0.053 | GeoNeXt | 2026-08-28 |
| DepthART: Scaling Foundation Monocular Depth to Tiny Models | ✓ Link | 0.964 | 0.059 | DepthART-S (zero-shot) | 2026-07-19 |
| ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device | ✓ Link | 0.933 | 0.084 | ZipDepth | 2026-07-09 |
| Let RGB Be the Language of Vision | ✓ Link | 0.927 | 0.086 | RINO-Zero (Qwen-Image-Edit) | 2026-07-14 |
| Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer | ✓ Link | 0.9045 | | MiDaS | 2019-07-02 |