LLVIP
by bupt-ai-cz
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
AI summary
Low-light dataset
A dataset and toolbox for low-light vision research, including image fusion and object detection tasks.
- stars
- 652
- forks
- 65
- watching
- 24
Similar projects
Found by comparing what the projects do, not just their names.
Image processor
An image processing library with low memory needs
Image processor
A Lua binding for a fast image processing library with low memory needs.
Image processor
A Python binding for an image processing library with parallel execution and memory-efficient design.
fyusion/llff1.6K
View synthesizer
Software for generating novel views from sparse light field data using deep learning and computer vision techniques.
Vision-Language Model Dataset
A collection of datasets and models designed to support the training of lite vision-language models.
Annotation API
An API for working with LVIS dataset annotations
Lidar sensor library
A MicroPython library for interacting with the Garmin Lidar Lite v3HP sensor
Lithography toolkit
Provides tools and algorithms for designing and optimizing optical lithography masks and images in the semiconductor industry
Image placeholder plugin
Generates low-quality image placeholders to reduce loading time and layout shifts in Vite applications.
Visual representation generator
A project that generates visual representations tailored for general visual reasoning, leveraging hierarchical scene descriptions and instance-level world knowledge.
Computer Vision Toolkit
A PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision.
Visual reasoning tool
A deep learning framework designed to improve visual reasoning capabilities by utilizing concepts and semantic relations.
LLM
An open-source implementation of a vision-language instructed large language model
Image processor
A Ruby binding for the libvips image processing library.
Image processor
A software framework for unprocessing images to enhance low-level computer vision tasks using color processing and deep neural networks.
