ssim_map — IMGMETRICS fidelity op

• Data kinds: image2d × image2d → image2d

• Call: import imgmetrics; imgmetrics.ssim_map(a, b, data_range=None, win_size=11, sigma=1.5, K1=0.01, K2=0.03, channel_axis=None, crop_border=True) (or opsimgmetrics.get("ssim_map"))

Usage

The SSIM map (before averaging) — to see *where* the two differ, as a picture.

> The detailed description below is the original text — the summary and the headings are translated.

`channel_axis` を指定するとチャネルごとに計算し、その平均マップを返す。

Detailed usage guide

• image_difference_metrics family guide

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

• The canonical algorithm (author, year) and its uses are named in the family usage guide above.

Runnable examples (verified samples that actually call this op)

• image_quality_metrics — py -3.11 examples/image_quality_metrics.py

Ops the type connects to (they accept image2d as input)

mse · rmse · psnr · ssim · ms_ssim · image_entropy · joint_entropy · mutual_information

Same category (fidelity)

mse · rmse · psnr · ssim · ms_ssim

*Provenance: imgmetrics.py — IMGMETRICS operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.