Manipulate run-length encoded image masks

The goal of the SAM Rock Fragmentation repository is to use the recent Segment Anything mask generator model created by MetaAI and implement it with an interface and set of algorithms to calculate …

A Gradio GUI and CLI tool for batch-downloading images from pixabay

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

the first public Martian rock dataset for segmentation.

Converts a depth map image to a normal map image using Python

Visible and Infrared Image Fusion Benchmark

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

An MIT License of YOLOv9, YOLOv7, YOLO-RD

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

ModelScope: bring the notion of Model-as-a-Service to life.

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

[CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

My awesome point cloud labeling tool

Open3D: A Modern Library for 3D Data Processing

Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

A small command line tool to simplify releasing software by updating all version strings in your source code by the correct increment and optionally commit and tag the changes.

A Python tool that transforms a 3D model / Mesh (in OBJ format) into a GIF file and into a CSS 3D Sprite image file using the Blender Python API and other tools.

Takes a Wavefront OBJ with textures and attempts to squash them into a single texture file.

Python script for converting 3D triangular mesh (obj) to image file (png) with MatPlotLib

Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

Run Segment Anything 2 (SAM 2) on macOS using Core ML models

Templates and example code for creating Streamlit Components

Optimized OpenAI's Whisper TFLite Port for Efficient Offline Inference on Edge Devices

Fast Multimodal LLM on Mobile Devices