Computer Vision & Object Detection AI Tools
Open-source models and libraries for object detection, image segmentation, depth estimation, pose estimation, and visual understanding.
Open-source models and libraries for object detection, image segmentation, depth estimation, pose estimation, and visual understanding.
Contrastive language-image pre-training model by OpenAI for zero-shot visual classification.
State-of-the-art real-time object detection supporting YOLOv5 through v11.
Open-set object detection combining DINO with grounded pre-training.
Cross-platform ML solutions by Google for face, hand, pose, and object detection.
Foundation model by Meta for promptable image and video segmentation.
The most widely-used open-source computer vision library with 2500+ algorithms.
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model by Intel ISL supporting multiple backbones.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Reusable computer vision tools for detection, tracking, and annotation by Roboflow.
Open-vocabulary real-time object detection using YOLO with text prompts.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Foundation model for promptable visual segmentation in images and videos with streaming memory.
Lightweight face recognition and analysis framework wrapping multiple models.
Real-time multi-person pose estimation by OpenMMLab with high accuracy.
Interactive tool for tracking and segmenting any object in video.
Meta AI research platform for object detection, segmentation, and pose estimation.
Monocular depth estimation model producing detailed depth maps from single images.
Open-source face analysis toolbox for recognition, detection, and alignment.
Combines Grounding DINO with SAM 2 for text-prompted segmentation and tracking.
Self-supervised vision transformer by Meta producing universal visual features.
Real-time multi-person pose estimation by CMU for body, hand, and face keypoints.
Additive angular margin loss for deep face recognition.
Original Segment Anything Model by Meta for zero-shot image segmentation.
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.
Robust multi-object tracking combining motion and appearance cues.