NVIDIA-AI-IOT / nanosamLinks
A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT
☆780Updated last year
Alternatives and similar repositories for nanosam
Users that are interested in nanosam are comparing it to the libraries listed below
Sorting:
- A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.☆354Updated 6 months ago
- ☆383Updated last year
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆206Updated last year
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,328Updated 3 months ago
- Run Segment Anything Model 2 on a live video stream☆461Updated 2 months ago
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆258Updated 11 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,417Updated 3 months ago
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆997Updated 6 months ago
- ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data☆365Updated 10 months ago
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆1,160Updated 2 weeks ago
- Segment Any RGBD☆847Updated 2 years ago
- Exporting Segment Anything, MobileSAM, and Segment Anything 2 into ONNX format for easy deployment☆349Updated last year
- Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!☆1,338Updated 6 months ago
- [AAAI 2025] Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"☆498Updated 6 months ago
- Efficient Track Anything☆597Updated 7 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,284Updated last month
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆420Updated last year
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆499Updated 8 months ago
- try to export sam2 to onnx.☆62Updated 2 months ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,550Updated last year
- TensorRT implementation of Depth-Anything V1, V2☆400Updated 4 months ago
- [CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects☆1,245Updated 3 weeks ago
- Muggled SAM: Segmentation without the magic☆151Updated 3 months ago
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆724Updated last year
- We developed a python UI based on labelme and segment-anything for pixel-level annotation. It support multiple masks generation by SAM(bo…☆377Updated last year
- code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction☆420Updated last year
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆868Updated 2 weeks ago
- CoRL 2024☆425Updated 9 months ago
- Quick start scripts and tutorial notebooks to get started with TAO Toolkit☆100Updated 2 weeks ago
- Tracking Any Point (TAP)☆1,598Updated last week