| Paper | Code | AbsRel | delta1 | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Vision as Unified Multimodal Generation | ✓ Link | 0.206 | 0.764 | SenseNova-Vision | 2026-07-07 |
| DepthART: Scaling Foundation Monocular Depth to Tiny Models | ✓ Link | 0.208 | 0.754 | DepthART-L (zero-shot) | 2026-07-19 |
| DepthART: Scaling Foundation Monocular Depth to Tiny Models | ✓ Link | 0.214 | 0.745 | DepthART-S (zero-shot) | 2026-07-19 |
| Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model | ✓ Link | 0.221 | 0.752 | Lotus-2 (zero-shot) | 2025-11-30 |
| AnyDepth: Depth Estimation Made Easy | ✓ Link | 0.226 | 0.736 | AnyDepth ViT-L | 2026-01-06 |
| ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device | ✓ Link | 0.226 | 0.739 | ZipDepth | 2026-07-09 |
| Video Generative Models as Geometry Learner | ✓ Link | 0.226 | 0.743 | GeoNeXt | 2026-08-28 |
| Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction | ✓ Link | 0.228 | 0.738 | Lotus-D (zero-shot) | 2024-09-26 |