RRepoGEO

REPOGEO REPORT · LITE

cszn/KAIR

Default branch master · commit fc1732f4 · scanned 6/30/2026, 7:17:05 AM

GitHub: 3,497 stars · 701 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface cszn/KAIR, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README's opening to highlight KAIR as a comprehensive PyTorch toolbox

    Why:

    CURRENT
    The README currently starts with a list of models and news updates.
    COPY-PASTE FIX
    Add the following as the very first line of the README, before any model lists or news: "KAIR is a comprehensive PyTorch toolbox and framework for state-of-the-art deep learning image restoration tasks, including denoising, super-resolution, deblurring, and more."
  • mediumabout#2
    Expand the repository description to emphasize its role as a comprehensive framework

    Why:

    CURRENT
    Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
    COPY-PASTE FIX
    KAIR: A comprehensive PyTorch toolbox and framework for state-of-the-art deep learning image restoration, including training and testing codes for models like DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR, and more.
  • lowtopics#3
    Add 'computer-vision' to repository topics

    Why:

    CURRENT
    bsrgan, deep-learning, denoising, dncnn, dpsr, esrgan, ffdnet, flops, image-restoration, pytorch, sisr, srmd, super-resolution, swinir, toolbox, usrnet
    COPY-PASTE FIX
    bsrgan, computer-vision, deep-learning, denoising, dncnn, dpsr, esrgan, ffdnet, flops, image-restoration, pytorch, sisr, srmd, super-resolution, swinir, toolbox, usrnet

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface cszn/KAIR
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
BasicSR
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. BasicSR · recommended 1×
  2. MMEditing · recommended 1×
  3. TorchSR · recommended 1×
  4. PyTorch-Image-Models (timm) · recommended 1×
  5. Albumentations · recommended 1×
  • CATEGORY QUERY
    Seeking a comprehensive PyTorch framework for various deep learning image restoration tasks.
    you: not recommended
    AI recommended (in order):
    1. BasicSR
    2. MMEditing
    3. TorchSR
    4. PyTorch-Image-Models (timm)
    5. Albumentations

    AI recommended 5 alternatives but never named cszn/KAIR. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I implement advanced deep learning models for image denoising and super-resolution in PyTorch?
    you: not recommended
    AI recommended (in order):
    1. PyTorch-Image-Models (timm) (rwightman/pytorch-image-models)
    2. BasicSR (xinntao/BasicSR)
    3. MMEditing (open-mmlab/mmediting)
    4. TorchVision (pytorch/vision)
    5. Albumentations (albumentations-team/albumentations)
    6. PyTorch Lightning (Lightning-AI/lightning)

    AI recommended 6 alternatives but never named cszn/KAIR. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of cszn/KAIR?
    pass
    AI named cszn/KAIR explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts cszn/KAIR in production, what risks or prerequisites should they evaluate first?
    pass
    AI named cszn/KAIR explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo cszn/KAIR solve, and who is the primary audience?
    pass
    AI named cszn/KAIR explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of cszn/KAIR. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/cszn/KAIR.svg)](https://repogeo.com/en/r/cszn/KAIR)
HTML
<a href="https://repogeo.com/en/r/cszn/KAIR"><img src="https://repogeo.com/badge/cszn/KAIR.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

cszn/KAIR — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite