MiDaS
Monocular depth estimation model by Intel ISL supporting multiple backbones.
About
MiDaS by Intel ISL estimates depth from a single image and is trained for strong zero-shot transfer by mixing many datasets during training. The latest MiDaS 3.1 supports several backbone architectures at different speed and accuracy trade-offs and works across diverse scenes on GPU or CPU. It is widely used as a depth-estimation component in graphics and vision pipelines. Released under the MIT 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
- MIT
- Added
- Apr 3, 2026
Related Tools
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model producing detailed depth maps from single images.
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.
Robust multi-object tracking combining motion and appearance cues.