NVIDIA-AI-IOT / nanosam
A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT
☆728Updated last year
Alternatives and similar repositories for nanosam:
Users that are interested in nanosam are comparing it to the libraries listed below
- A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.☆312Updated last month
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆913Updated 2 months ago
- ☆377Updated last year
- Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything☆1,235Updated 4 months ago
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆228Updated 6 months ago
- Run Segment Anything Model 2 on a live video stream☆320Updated last month
- CoRL 2024☆386Updated 4 months ago
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆402Updated 10 months ago
- We developed a python UI based on labelme and segment-anything for pixel-level annotation. It support multiple masks generation by SAM(bo…☆363Updated last year
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆184Updated last year
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆694Updated last year
- Export Segment Anything Models to ONNX☆325Updated 7 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆1,877Updated 3 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆946Updated last week
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,343Updated 7 months ago
- [AAAI 2025] Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"☆459Updated 2 months ago
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,285Updated last year
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,473Updated 8 months ago
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆937Updated 2 months ago
- Segment Any RGBD☆818Updated last year
- Efficient Track Anything☆500Updated 2 months ago
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆470Updated 4 months ago
- [CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects☆1,152Updated 2 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,526Updated 8 months ago
- Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!☆1,146Updated 2 months ago
- TensorRT implementation of Depth-Anything V1, V2☆340Updated 2 weeks ago
- Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".☆563Updated last year
- [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim☆325Updated last month
- [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects☆1,889Updated 2 weeks ago
- The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…☆1,659Updated last week