检测 / 分割

Real-time 3D LiDAR obstacle detection, tracking & trajectory prediction for ROS 1 / ROS 2: ground segmentation, clustering, 2.5D occupancy, optional GPU CenterPoint (TensorRT). ~10 ms/scan on one CPU core.

[AAAI2026] X-SAM: From Segment Anything to Any Segmentation

[IEEE Transactions on Medical Imaging/TMI 2023] This repo is the official implementation of "LViT: Language meets Vision Transformer in Medical Image Segmentation"

[CVPR 2023] Label-Free Liver Tumor Segmentation

YOLOv8 Object Tracking Using PyTorch, OpenCV and Ultralytics

Python package for segmenting LiDAR data using Segment-Anything Model (SAM) from Meta AI.

Flood-Filling Networks for instance segmentation in 3d volumes.

[RA-L] Traversable ground and above-ground object segmentation using graph representation of 3D LiDAR scans

Based on tensorrt v8.0+, deploy detection, pose, segment, tracking of YOLO11 with C++ and python api.

Anime Video Toolkit: AI upscale, RIFE interpolation and restore in one pass. CLI, Standalone and After Effects.

Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)

ROS 2 wrapper for the ZED SDK

A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

YOLOX + ROS2 object detection package (C++ only support)

ML model optimization product to accelerate inference.

[CVPR 2023 Highlight] LaserMix for Semi-Supervised LiDAR Semantic Segmentation

[NeurIPS 2025 Spotlight] A Generalist Diffusion Model for Vision Perception

U-Time: A Fully Convolutional Network for Time Series Segmentation

A lexicon for Sudachi

NVIDIA DeepStream Monorepo: DeepStream SDK and reference apps for building GPU‑accelerated, real-time video and multi‑sensor analytics pipelines with GStreamer, TensorRT, and vision AI models across edge, on‑prem, and cloud deployments.

MIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

Technology-invariant pipeline for spatial omics analysis that scales to millions of cells (Xenium / Visium HD / MERSCOPE / CosMx / PhenoCycler / MACSima / etc.)

[CVPR 2025] SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures

Colour checker detection with Python

Build a complete experiment pipeline for your PyTorch MIP model in 10 seconds.

Ultralytics YOLO tutorials for Colab, Kaggle, and SageMaker covering training, inference, export, and vision tasks.

A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

All Computer Vision Projects - Beginner to Advanced

Real-time object detection, keypoint estimation, instance and semantic segmentation. Train, export (TensorRT, ONNX, OpenVINO, CoreML), deploy. Apache-2.0

Unofficial notebooks and resources for Microsoft's Florence-2 vision-language model: inference, auto-labelling and fine-tuning.

High-performance Ultralytics YOLO inference in Rust with ONNX Runtime, GPU backends, CLI, and WebGPU/WASM.

Production-ready C++/TensorRT inference engine for RF-DETR. Object detection and instance segmentation with FP32/FP16/INT8 support. Optimized for NVIDIA GPUs, Jetson (Orin, AGX Thor).

NVIDIA-accelerated, deep learned model support for image space object detection