 vmaf
 vmaf 
 Video quality evaluator
 An Emmy-winning video quality assessment algorithm developed by Netflix.
Perceptual video quality assessment based on multi-method fusion.
5k stars
 495 watching
 756 forks
 
Language: Python 
last commit: 12 months ago 
Linked from   1 awesome list  
 Related projects:
| Repository | Description | Stars | 
|---|---|---|
|  | Provides state-of-the-art video understanding codebase with efficient training methods and pre-trained models for various tasks | 6,680 | 
|  | Comprehensive benchmark for evaluating multi-modal large language models on video analysis tasks | 422 | 
|  | A video pose and shape estimation method that predicts body parameters for each frame of an input video. | 2,911 | 
|  | A tool to evaluate video language models' ability to understand and describe video content | 91 | 
|  | A modern Python framework for building high-performance RESTful APIs | 78,676 | 
|  | A collection of libraries and tools to process multimedia content | 46,702 | 
|  | An implementation of video matting with temporal guidance using recurrent neural networks and various deep learning frameworks. | 8,657 | 
|  | A comprehensive video understanding toolbox and benchmark with modular design, supporting various tasks such as action recognition, localization, and retrieval. | 4,360 | 
|  | A Python wrapper that simplifies the use of FFmpeg's filtering capabilities in video processing | 10,147 | 
|  | A model for tracking any point on a video using transformer-based architecture and optical flow benefits | 3,978 | 
|  | An open-source benchmarking framework for evaluating cross-style visual capability of large multimodal models | 84 | 
|  | Software to interpolate blurry video frames and enhance image quality | 209 | 
|  | High-quality implementations of reinforcement learning algorithms for research and development purposes | 15,885 | 
|  | A multimedia framework that provides an easy-to-use API for building video players across multiple platforms. | 4,001 | 
|  | Evaluates and benchmarks large language models' video understanding capabilities | 121 |