1.Tencent / WeVisOne-VL
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.
+372 stars
from 310 · score 5.92
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
20 repositories by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
2.ultralytics / ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
- ultralytics
- yolov8
- yolo
- deep-learning
- image-classification
- machine-learning
- +14 more
+181 stars
from 62,910 · score 5.20
3.danielgatis / rembg
Rembg is a tool to remove images background
- image-processing
- background-removal
- python
+115 stars
from 25,206 · score 4.75
4.Shuyun-Wang / MatAnyone-E
MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
+108 stars
from 55 · score 4.69
5.facebookresearch / sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+71 stars
from 12,123 · score 4.28
6.facebookresearch / sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+31 stars
from 20,066 · score 3.47
+30 stars
from 14,979 · score 3.43
8.facebookresearch / segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+29 stars
from 55,069 · score 3.40
9.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
- yolov5
- object-detection
- pytorch
- onnx
- coreml
- tflite
- +10 more
+19 stars
from 58,231 · score 3.00
10.milesial / Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
- pytorch
- unet
- pytorch-unet
- semantic-segmentation
- convolutional-networks
- kaggle
- +5 more
+16 stars
from 11,731 · score 2.83
11.opencoredev / bg0
Private, unlimited background removal that runs in your browser.
+15 stars
from 473 · score 2.77
12.Evergreen0929 / S4VY
The official implementation of 'S4VY: Segment Anything in Feed-Forward 4D Visual Geometry'
+15 stars
from 156 · score 2.77
13.lillyguisnet / sam3-segmentation
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
- codex
- computer-vision
- +4 more
+15 stars
from 107 · score 2.77
14.facebookresearch / detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
+13 stars
from 34,952 · score 2.64
15.open-mmlab / mmdetection
OpenMMLab Detection Toolbox and Benchmark
- object-detection
- instance-segmentation
- fast-rcnn
- faster-rcnn
- mask-rcnn
- cascade-rcnn
- +14 more
+9 stars
from 33,013 · score 2.30
16.PaddlePaddle / PaddleDetection
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
- yolov3
- blazeface
- +14 more
+9 stars
from 14,447 · score 2.30
17.qubvel-org / segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
- segmentation
- image-processing
- pspnet
- unet
- unet-pytorch
- pytorch
- +14 more
+6 stars
from 11,785 · score 1.95
18.IDEA-Research / Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
- open-vocabulary-detection
- open-vocabulary-segmentation
- data-generation
- automatic-labeling-system
- caption
- speech
- +2 more
+2 stars
from 17,788 · score 1.10
19.dbolya / yolact
A simple, fully convolutional model for real-time instance segmentation.
- realtime
- real-time
- instance-segmentation
- yolact
- pytorch
+1 stars
from 5,250 · score 0.69
20.visionml / pytracking
Visual tracking library based on PyTorch.
- computer-vision
- tracking
- machine-learning
- visual-tracking
+1 stars
from 3,524 · score 0.69