Task
Depth Estimation
D
TIM2333ll/Depth-Anything-V2-Base
Depth Estimation·TIM2333ll· 8
Introduction Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-b
# pull & run locally
pip install mlforge-sdk && mlforge pull TIM2333ll/Depth-Anything-V2-Base
pip install mlforge-sdk && mlforge pull TIM2333ll/Depth-Anything-V2-Base
Model details
Provider
TIM2333ll
Framework
depth-anything-v2
Size
372 MB
License
cc-by-nc-4.0
Downloads
8
Paper
arXiv:2406.09414
Updated
2026-05-07
About TIM2333ll/Depth-Anything-V2-Base
Introduction Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-based models - impressive fine-tuned performance with our pre-trained models
Related Depth Estimation
D
depth-anything/Depth-Anything-V2-Small-hf
1.7M 38
🤗 HF
D
depth-anything/DA3METRIC-LARGE
771.6K 19
🤗 HF
D
LiheYoung/depth-anything-large-hf
388.9K 65
🤗 HF
D
Intel/dpt-hybrid-midas
225.1K 112
🤗 HF
D
depth-anything/DA3NESTED-GIANT-LARGE-1.1
199.9K 27
🤗 HF
D
depth-anything/Depth-Anything-V2-Large-hf
199.1K 32
🤗 HF