EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
☆701Aug 11, 2026Updated 2 months ago
Alternatives and similar repositories for efficientsam3
Users that are interested in efficientsam3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TensorRT Engine for SAM-3 model by Meta AI☆232Jul 2, 2026Updated 3 months ago
- Using C++ TensorRT for SAM3 model inference☆121Jul 1, 2026Updated 3 months ago
- [CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"☆1,008Jan 27, 2026Updated 9 months ago
- ONNX export and inference for SAM3.☆110Updated 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
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [ICLR 2026] The official implementation of "Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval"☆49Feb 9, 2026Updated 8 months ago
- [DEIMv2] Real Time Object Detection Meets DINOv3☆2,083Oct 23, 2026Updated last week
- Efficient Track Anything☆832Jan 6, 2025Updated last year
- Detect Anything in Real Time: Real-time object detection using frontier object detection models.☆796Oct 6, 2026Updated 3 weeks ago
- ☆31Jul 4, 2026Updated 3 months ago
- [CVPR2026] Detect Anything via Next Point Prediction☆1,631Feb 22, 2026Updated 8 months ago
- Decoupled Memory Selection for Multi-target Video Segmentation of SAM3☆63Jan 16, 2026Updated 9 months ago
- [ECCV 2026] Real-Time Interactive Multi-Target Video Segmentation☆71Jul 10, 2026Updated 3 months ago
- Finetune SAM3 with LoRA — optimized for images. A simple setup for training SAM3 on image datasets. Video finetuning is not yet supported…☆294Aug 23, 2026Updated 2 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.
- [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).☆637Oct 12, 2026Updated 2 weeks ago
- Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized…☆733Apr 14, 2026Updated 6 months ago
- Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"☆1,177May 24, 2025Updated last year
- [TMLR 26] EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation☆371Oct 22, 2026Updated last week
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,987Oct 6, 2026Updated 3 weeks ago
- [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
- Reference PyTorch implementation and models for DINOv3☆11,649Jul 15, 2026Updated 3 months ago
- SAM 2++: Tracking Anything at Any Granularity☆73Dec 15, 2025Updated 10 months ago
- Official code and resources for SAM3-I.☆189Apr 14, 2026Updated 6 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- YOLOE: Real-Time Seeing Anything [ICCV 2025]☆2,325Jun 26, 2025Updated last year
- All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.☆1,726Updated this week
- [ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".☆596Apr 17, 2026Updated 6 months ago
- [CVPR 2026 Oral] "INSID3: Training-Free In-Context Segmentation with DINOv3"☆787Jun 26, 2026Updated 4 months ago
- D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]☆3,383Oct 5, 2026Updated 3 weeks ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,403Apr 13, 2026Updated 6 months ago
- ☆35Nov 10, 2025Updated 11 months ago
- [CVPR 2026] Official code and models for Video Encoder-only Mask Transformer (VidEoMT).☆272Sep 4, 2026Updated last month
- Fast state-of-the-art image and video segmentation in portable C/C++☆378Sep 16, 2026Updated last month
- 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.
- Vision as Unified Multimodal Generation☆722Sep 1, 2026Updated last month
- This repository contains the implementation of SAM3 trackers.☆39Jun 30, 2026Updated 4 months ago
- Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.☆792Sep 11, 2026Updated last month
- Export and run SAM, MobileSAM, EfficientSAM, SAM 2/2.1, and SAM 3 as ONNX for portable image segmentation☆433Aug 30, 2026Updated 2 months ago
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆14,582May 19, 2026Updated 5 months ago
- This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!☆5,904May 5, 2026Updated 5 months ago
- Depth Anything 3☆6,600Jul 27, 2026Updated 3 months ago