Depth Anything V2
Monocular depth estimation model producing detailed depth maps from single images.
About
Depth Anything V2 by HKU and TikTok improves on V1 with finer detail and more reliable monocular depth estimation, while keeping faster inference, fewer parameters, and higher accuracy than diffusion-based depth models. It comes in four scales from small to large for relative depth and can be loaded through Hugging Face Transformers. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Foundation model for monocular depth estimation by TikTok.
Improved vision-language model by Google using sigmoid loss for contrastive learning.
Open-vocabulary object detection model by Google using vision transformers.
OpenMMLab detection toolbox with 300+ pre-trained models and 80+ algorithms.
State-of-the-art real-time object detection supporting YOLOv5 through v11.
Additive angular margin loss for deep face recognition.