Download
butteraugli is a perceptual similarity metric designed to estimate how noticeable differences between two images will be to the human eye. Instead of simple pixel math, it models aspects of human vision—color sensitivity, spatial masking, and contrast perception—to highlight differences that viewers actually see. The core tool outputs a single “distance” score along with per-pixel or per-region maps that show where artifacts are most objectionable. These maps make it practical to tune compressor settings and confirm whether bitrate reductions are visually acceptable. The metric has become a common yardstick for objective image quality when comparing codecs or encoder tweaks that target web or mobile delivery. Because it is deterministic and fast, it can be used in automated pipelines to gate releases on visual quality, not just file size.
Features
- Human-perception-oriented distance score between images
- Heatmaps that localize visually objectionable differences
- Useful for codec comparison and encoder tuning
- Deterministic, automation-friendly CLI tool and library
- Sensitivity to color, contrast, and spatial masking effects
- Works as a quality gate in build or compression pipelines
Project Samples
