[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
☆1,008Jan 27, 2026Updated 9 months ago
Alternatives and similar repositories for EdgeTAM
Users that are interested in EdgeTAM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Efficient Track Anything☆834Jan 6, 2025Updated last year
- [CVPR 2025, IJCV 2026] "A Distractor-Aware Memory for Visual Object Tracking with SAM2", "Distractor-Aware Memory-Based Visual Object Tra…☆503Sep 25, 2026Updated last month
- EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept s…☆701Aug 11, 2026Updated 2 months ago
- Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"☆1,177May 24, 2025Updated last year
- Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"☆7,119Mar 18, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆790Jul 17, 2025Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,403Apr 13, 2026Updated 6 months ago
- Depth Anything 3☆6,604Jul 27, 2026Updated 3 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆20,080May 30, 2026Updated 5 months ago
- Reference PyTorch implementation and models for DINOv3☆11,651Jul 15, 2026Updated 3 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆3,108Oct 24, 2026Updated last week
- [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching☆2,975Dec 19, 2025Updated 10 months ago
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆2,325Jun 26, 2025Updated last year
- This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!☆5,905May 5, 2026Updated 5 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [CVPR 2026] Official code and models for Video Encoder-only Mask Transformer (VidEoMT).☆272Sep 4, 2026Updated last month
- [DEIMv2] Real Time Object Detection Meets DINOv3☆2,083Oct 23, 2026Updated last week
- RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning…☆9,938Updated this week
- The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading t…☆12,149Oct 23, 2026Updated last week
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆3,865Aug 7, 2026Updated 2 months ago
- Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0…☆3,968Updated this week
- Code for "LiftFeat: 3D Geometry-Aware Local Feature Matching", ICRA2025☆259Sep 23, 2025Updated last year
- [CVPR 2025 Highlight] "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"☆387Sep 25, 2025Updated last year
- CoTracker is a model for tracking any point (pixel) on a video.☆5,181Mar 3, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ECCV 2026] Real-Time Interactive Multi-Target Video Segmentation☆71Jul 10, 2026Updated 3 months ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,376May 1, 2025Updated last year
- [SENSORS 2025] PicoSAM2 and PicoSAM3 are segmentation models running in-sensor on the Sony IMX500.☆58Oct 8, 2026Updated 3 weeks ago
- AllTracker is a model for tracking all pixels in a video.☆435May 8, 2026Updated 5 months ago
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆923Nov 20, 2023Updated 2 years ago
- [ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking☆524Nov 3, 2025Updated 11 months ago
- [ICLR 2026] Official implementation of "SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction"☆302Mar 27, 2026Updated 7 months ago
- Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025, Highlight)☆882Mar 18, 2026Updated 7 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆3,800Nov 11, 2025Updated 11 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,156Sep 10, 2026Updated last month
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction☆345Sep 16, 2026Updated last month
- [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos☆2,311Oct 7, 2025Updated last year
- Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!☆1,757Jan 15, 2025Updated last year
- [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass☆1,592May 7, 2025Updated last year
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆288Aug 29, 2024Updated 2 years ago
- SAM 2++: Tracking Anything at Any Granularity☆73Dec 15, 2025Updated 10 months ago