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.
☆4,552Updated 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☆8,630Updated last week
- SAM 3D Objects☆4,025Updated last week
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,290Updated 4 months ago
- [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning☆1,417Updated 5 months ago
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆1,922Updated 5 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆3,073Updated 3 weeks ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆2,503Updated 3 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆1,776Updated 2 months ago
- Depth Anything 3☆3,001Updated this week
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,351Updated 7 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,403Updated last week
- The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints …☆1,902Updated last week
- All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.☆1,122Updated this week
- Efficient Track Anything☆675Updated 10 months ago
- [CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"☆815Updated 3 weeks ago
- Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)☆883Updated last week
- [DEIMv2] Real Time Object Detection Meets DINOv3☆1,089Updated 3 weeks ago
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆1,592Updated last month
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆1,061Updated 10 months ago
- The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"☆670Updated 7 months ago
- Run Segment Anything Model 2 on a live video stream☆540Updated 6 months ago
- Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.☆1,166Updated 4 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,048Updated last month
- About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]☆819Updated 5 months ago
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆2,310Updated last month
- RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tun…☆4,545Updated 2 weeks ago
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆444Updated last month
- [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling☆4,102Updated 2 months ago
- [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching☆2,281Updated last month
- [CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence☆1,309Updated 2 months ago