BRISQUE (Blind/Referenceless Image Spatial Quality Evaluator, IEEE TIP 2012) is a classic handcrafted no-reference image-quality model built on natural scene statistics, the finding that undistorted natural images obey consistent statistical regularities that blur, noise, and compression measurably break. It works in the spatial domain from locally normalized luminance coefficients, scoring how far a frame has drifted from natural-looking statistics. Unlike the training-free NIQE, BRISQUE is opinion-aware: it is trained on a set of distorted images that humans have rated, so it learns the mapping from statistical deviation to perceived quality. It scores a single frame, so for video it is run per frame and the results are pooled, and it is available through toolboxes such as pyiqa and scikit-video. Its catch is that, tuned on photographic distortions, it correlates poorly with human judgment on in-the-wild user-generated video, with reported cross-dataset SROCC around 0.31 to 0.58, so its number must be validated on content like yours.
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
BRISQUE helps when there is no reference to compare against, such as user uploads or live camera feeds, but its single-frame score misses motion artifacts. Our seven-volume handbook covers the whole video stack; for BRISQUE start with Volume 1 on quality metrics and compression, with Volume 6 on AI models and Volume 3 on QoE monitoring. Written by Nikolay Sapunov, CEO at Fora Soft.
Scoring user-uploaded video without a reference and considering BRISQUE?
Send us sample clips and we will compare BRISQUE with other no-reference metrics on your content and recommend a scoring setup with thresholds. 250+ video products shipped since 2005.
