# Enhancing VMAF through New Feature Integration and Model Combination

arXiv: https://arxiv.org/abs/2103.06338 · HTML: https://mlsanity.com/paper/2103.06338/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 29 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 1 of 1)

- [SpatioTemporal Feature Integration and Model Fusion for Full Reference Video Quality Assessment](https://mlsanity.com/paper/1804.04813/) (2018)

## Built on by (most cited first, 7 of 7)

- [FUNQUE: Fusion of Unified Quality Evaluators](https://mlsanity.com/paper/2202.11241/) (2022)
- [A FUNQUE Approach to the Quality Assessment of Compressed HDR Videos](https://mlsanity.com/paper/2312.08524/) (2023)
- [BVI-UGC: A Video Quality Database for User-Generated Content Transcoding](https://mlsanity.com/paper/2408.07171/) (2024)
- [RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment](https://mlsanity.com/paper/2312.08864/) (2023)
- [A review on Machine Learning based User-Centric Multimedia Streaming Techniques](https://mlsanity.com/paper/2411.15801/) (2024)
- [A Mamba-based Perceptual Loss Function for Learning-based UGC Transcoding](https://mlsanity.com/paper/2603.25566/) (2026)
- [FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs](https://mlsanity.com/paper/2604.24123/) (2026)

## Abstract (arXiv)

VMAF is a machine learning based video quality assessment method, originally designed for streaming applications, which combines multiple quality metrics and video features through SVM regression. It offers higher correlation with subjective opinions compared to many conventional quality assessment methods. In this paper we propose enhancements to VMAF through the integration of new video features and alternative quality metrics (selected from a diverse pool) alongside multiple model combination. The proposed combination approach enables training on multiple databases with varying content and distortion characteristics. Our enhanced VMAF method has been evaluated on eight HD video databases, and consistently outperforms the original VMAF model (0.6.1) and other benchmark quality metrics, exhibiting higher correlation with subjective ground truth data.