paper-with-me

Papers

Hacking VMAF and VMAF NEG: vulnerability to different preprocessing methods

2021-07-09 · Maksim Siniukov, Anastasia Antsiferova, Dmitriy Kulikov, Dmitriy Vatolin

Video-quality measurement plays a critical role in the development of video-processing applications. In this paper, we show how video preprocessing can artificially increase the popular quality metric VMAF and its tuning-resistant version, VMAF NEG. We propose a pipeline that tunes processing-algorithm parameters to increase VMAF by up to 218.8%. A subjective comparison revealed that for most preprocessing methods, a video's visual quality drops or stays unchanged. We also show that some preprocessing methods can increase VMAF NEG scores by up to 23.6%.

📄 PDF Abstract BibTeX arXiv:2107.04510

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VMAF Re-implementation on PyTorch: Some Experimental Results

2023-10-24 · Kirill Aistov, Maxim Koroteev

Based on the standard VMAF implementation we propose an implementation of VMAF using PyTorch framework. For this implementation comparisons with the standard (libvmaf) show the discrepancy $\lesssim 10^{-2}$ in VMAF unit…

AudioVMAF: Audio Quality Prediction with VMAF

2023-08-07 · Arijit Biswas, Harald Mundt

Video Multimethod Assessment Fusion (VMAF) [1], [2], [3] is a popular tool in the industry for measuring coded video quality. In this study, we propose an auditory-inspired frontend in existing VMAF for creating videos o…

Prediction

Kelvin v1.0: A Neural Pre-Encoder for H.264: A standards-compliant learned preprocessor with -27.62% BD-VMAF on UVG

2026-05-10 · Marco Graziano arxiv

Kelvin is a lightweight learned pre-encoder that sits in front of an unmodified libx264 encoder. It applies content-adaptive pixel adjustments, bounded at +/-1/255 per channel, so that the encoder allocates bits where th…

Enhancing VMAF through New Feature Integration and Model Combination

2021-03-10 · Fan Zhang, Angeliki Katsenou, Christos Bampis, Lukas Krasula 외

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 correl…

regressionVideo Quality Assessment

Towards properties of adversarial image perturbations

2025-03-18 · Egor Kuznetsov, Kirill Aistov, Maxim Koroteev

Using stochastic gradient approach we study the properties of adversarial perturbations resulting in noticeable growth of VMAF image quality metric. The structure of the perturbations is investigated depending on the acc…

Image Restoration