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
Simple and effective multi-object tracking using every detection box.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Monocular depth estimation model by Intel ISL supporting multiple backbones.
Robust multi-object tracking combining motion and appearance cues.