Mc-Cnn

Visit Tool

mc-cnn is an open-source research tool that provides procedures for stereo matching using convolutional neural networks. It includes methods for computing matching costs and training CNNs, along with a basic stereo method.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is mc-cnn?

mc-cnn is an open-source project hosted on GitHub, offering a comprehensive set of procedures for stereo matching tasks utilizing convolutional neural networks. It enables users to compute stereo matching costs and train CNNs for this purpose. The tool also integrates a basic stereo method that incorporates cross-based cost aggregation, semiglobal matching, left-right consistency checks, median filtering, and bilateral filtering. It requires a powerful NVIDIA GPU with at least 6 GB of memory for KITTI datasets and 12 GB for Middlebury datasets, supporting GTX Titan, K80, and GTX Titan X. The repository provides detailed instructions for installation, running pre-trained networks, training on KITTI and Middlebury datasets, and experimenting with different network architectures.

Best used for

Ideal for researchers and academics who need to implement and evaluate stereo matching algorithms using convolutional neural networks, train custom CNNs on established datasets like KITTI and Middlebury, and experiment with different network architectures. Especially valuable for computer vision research and development.

Common actions

perform stereo matching

train neural networks

evaluate computer vision models

research image processing

face swapping"AI Agents"github copilotautomated workflowdeepfakecollaborationopen-sourceworkflowslow-code/no-code

Capabilities

Key features

Compute stereo matching cost
Train convolutional neural networks
Basic stereo method
Pre-trained network downloads
KITTI dataset support
Middlebury dataset support

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What hardware is required to run mc-cnn?

To run mc-cnn, you need an NVIDIA GPU. For the KITTI dataset, at least 6 GB of memory is required, while the Middlebury dataset demands 12 GB. The code has been tested on GTX Titan, K80, and GTX Titan X GPUs.

What software dependencies does mc-cnn have?

mc-cnn requires Torch, OpenCV 2.4, and png++ for compilation and execution. Additionally, ImageMagick is needed for preprocessing steps, particularly for resizing images when working with the Middlebury dataset.

Can I train my own convolutional neural networks with mc-cnn?

Yes, mc-cnn provides procedures to train convolutional neural networks on both the KITTI and Middlebury datasets. You can also experiment with different network architectures by modifying parameters like the number of layers and feature maps.

Trending

Subcategories trending in Research & Education

Study Assistants Knowledge Management Course Creation Scientific Computing Summarization Language Learning

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