Effortless data labeling with AI support from Segment Anything and other awesome models.

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

使用onnxruntime部署GroundingDINO开放世界目标检测，包含C++和Python两个版本的程序

juxtapose: Multi-Person Pose Tracking Inference SDK with RTMDet, YOLOv8, GDino, RTMPose (ONNX) & Trackers (ByteTrack & BotSORT) & Tapnet with custom ROIs + FastAPI GPU exe

Extract objects from images or video via text prompt

This project represents a GroundingDINO Inference (zero-shot object detection) procedure with both methods (CLI and Script). This implementation will help the reader to know the sequence of commands and exemplifying commands for running a quick zero-shot object detection. Additionally, the reader may get insight into code (script) execution.

Support batch inference of Grounding DINO. "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Prompt based automatic annotation

language‑guided object detection that outputs a single pick target for robotic pick‑and‑place tasks

Open vocabulary object detection using GroundingDINO with natural language prompts.

Run GroundingDINO as a local REST API using Docker. Easily send images and text prompts for object grounding.

VLM-assisted object detection, COCO dataset generation, and YOLO fine-tuning tools.

Open-vocabulary part detection + LLM reasoning for context-aware AR assembly instructions — GroundingDINO + Llama 3.2 + Unity JSON output

Image-Position-Editing is a image processing tool for generating segmented masks, changing object positions, and removing objects from images with text prompt

Dorsal fin segmentation and matching with Grounded SAM and SIFT / Hu-moments

image repainting using SAM,groundingDINO and stableDiffusion

A customizable pipeline for eye tracking in the wild via Grounded Segment Anything

A Clothing Similarity Detection System