facebookresearch / sam3Links
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.
☆7,527Updated last week
Alternatives and similar repositories for sam3
Users that are interested in sam3 are comparing it to the libraries listed below
Sorting:
- Reference PyTorch implementation and models for DINOv3☆9,525Updated 2 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆3,255Updated 2 months ago
- SAM 3D Objects☆5,869Updated last week
- The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints …☆2,574Updated last month
- Depth Anything 3☆4,283Updated last month
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,334Updated 6 months ago
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆2,029Updated 7 months ago
- [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning☆1,448Updated 7 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,147Updated 2 weeks ago
- [ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for…☆5,527Updated this week
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆2,954Updated 5 months ago
- [DEIMv2] Real Time Object Detection Meets DINOv3☆1,463Updated last month
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆2,885Updated 3 weeks ago
- Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)☆1,119Updated 2 weeks ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,505Updated last week
- All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.☆1,290Updated this week
- Efficient Track Anything☆775Updated last year
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,267Updated 3 months ago
- [CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"☆868Updated 2 weeks ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,362Updated 9 months ago
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆1,083Updated last year
- SAM with text prompt☆2,532Updated 5 months ago
- [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation☆7,579Updated last year
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆1,744Updated 4 months ago
- Run Segment Anything Model 2 on a live video stream☆564Updated 8 months ago
- ViPE: Video Pose Engine for Geometric 3D Perception☆1,701Updated last month
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,808Updated 7 months ago
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆12,417Updated 4 months ago
- [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling☆4,231Updated 4 months ago
- CoTracker is a model for tracking any point (pixel) on a video.☆4,820Updated last year