SMOKE

Visit Tool

SMOKE is an AI Agents & Automation tool that provides single-stage monocular 3D object detection via keypoint estimation. It achieves real-time performance for autonomous driving applications.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is SMOKE?

SMOKE is an open-source, real-time monocular 3D object detector specifically designed for autonomous driving applications. It utilizes a single-stage approach via keypoint estimation to achieve efficient and accurate 3D object detection from a single camera. The system boasts a runtime of approximately 30ms on an NVIDIA TITAN XP GPU. SMOKE's performance has been evaluated on the KITTI 3D detection dataset, showing competitive results for detecting cars, pedestrians, and cyclists. The project provides pretrained weights and detailed setup instructions for researchers and developers, building upon components from CenterNet, maskrcnn-benchmark, and Detectron2.

Best used for

Ideal for developers and data scientists who need to implement real-time 3D object detection from a single camera, integrate advanced perception into autonomous driving systems, and conduct research in monocular 3D object detection. Especially valuable for projects requiring high performance and open-source flexibility.

Common actions

detect 3D objects

implement computer vision

develop autonomous systems

collaborationopen-sourceworkflowsface swappinggithub copilotlow-code/no-codedeepfakeautomated workflow"AI Agents"

Capabilities

Key features

Single-stage 3D object detection
Monocular input
Keypoint estimation
Real-time performance
Autonomous driving focus
Pretrained weights available

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of performance can I expect from SMOKE?

SMOKE is designed for real-time applications, achieving a runtime of approximately 30ms on a single NVIDIA TITAN XP GPU. It provides competitive performance on the KITTI 3D detection benchmark for various object categories like cars, pedestrians, and cyclists.

What are the system requirements to run SMOKE?

The project is tested under Ubuntu 16.04 with Python 3.7, Pytorch 1.3.1, and CUDA 10.0. Users will also need to download and organize the KITTI 3D Object Dataset for training and testing.

Does SMOKE provide pretrained models?

Yes, pretrained weights for SMOKE are available for download. These weights can be used to quickly get started with the model for inference or as a base for further fine-tuning on specific datasets.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce