Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Repository Index
89,572 visible repositories in the index
1–24 of 24 · Most stars
OpenMMLab Detection Toolbox and Benchmark
- object-detection
- instance-segmentation
- fast-rcnn
- faster-rcnn
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
- mask-rcnn
- tensorflow
- object-detection
- instance-segmentation
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
- object-detection
- instance-segmentation
- faster-rcnn
- mask-rcnn
Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
- semantic-segmentation
- image-segmentation
- image-matting
- interactive-segmentation
High-resolution models for human tasks.
[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation
- visual-tracking
- video-object-segmentation
- read-time
- pytorch
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
- fcos
- blendmask
- abcnet
- object-detection
Mask RCNN in TensorFlow
- maskrcnn
- rcnn
- fasterrcnn
- tensorflow
[IEEE TMI Best Paper Award] Official Implementation for UNet++
- medical-imaging
- segmentation
- unet
- biomedical-imaging
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
An extension of Open3D to address 3D Machine Learning tasks
- 3d-perception
- datasets
- pretrained-models
- lidar
The repository host gives no description.
Official Pytorch implementation of the preprint paper "Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos", in arXiv:2010.11800.
- dynamic-sky-replacement
- sky-matting
- harmonization
- skyar
Codes for paper "Mask Scoring R-CNN".
An MXNet implementation of Mask R-CNN
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"
- instance-segmentation
- object-detection
- panoptic-segmentation
- semantic-segmentation
Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts
- 2d-segmentation
- adapter
- camouflage-images
- camouflaged-object-detection
WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level and pixel-level perception from points and boxes to masks and alpha mattes.
NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
- mllm
- multimodal-large-language-models
- segmentation
Usiigaci: stain-free cell tracking in phase contrast microscopy enabled by supervised machine learning
- tensorflow
- python3
- keras
- resnet-101
Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.
- agent-skills
- annotation
- claude-code
- claude-code-plugin
Implementation of the Mask R-CNN model using OCaml's numerical library Owl.