Skip to content

Official Code for "Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model". A SOTA algorithm in low-light image enhancement, underwater image enhancement, and backlit image enhancement.

active 2023-11-212026-05-25 (UTC)

Partial coverage19,060 / 24,521 hourly files (78%) · 2 absent upstream · 5,459 failed, retryable2023-10-262026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
75
Pushes
3
Pull requests
0
Issues
11
Stars
56
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 917 days from 2023-11-21 to 2026-05-25. Pushes: 3 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 11 total, peak 4 in a day. Comments: 3 total, peak 1 in a day. Stars: 56 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
cnyvfang5301
ChunmingHe4001
AXNing2000
Lownzp1000
GaoZY-20001000
JianghaiSCU1000
keeeepreal1000
ZhengkaiZhao1001
10139904241000

Recent activity

Latest issues, pull requests and releases

  • Issue#12keeeepreal2025-07-31 20:56
    About the Retinex prior extraction(PRE) module
  • Issue#10GaoZY-20002025-03-18 02:35
    关于LLIE S1训练问题
  • Issue comment#9ZhengkaiZhao2025-03-15 15:24
    About the pre-training model
  • Issue#8AXNing2025-03-02 06:43
    Does the training code for Stage S1 not match the description in the paper?
  • Issue#8AXNing2025-03-02 06:23
    Does the training code for Stage S1 not match the description in the paper?
  • Issue comment#5cnyvfang2025-02-23 19:05
    No object named 'DiffIRS1_Cross' found in 'arch' registry!
  • Issue#5cnyvfang2025-02-23 19:05
    No object named 'DiffIRS1_Cross' found in 'arch' registry!
  • Issue#4Lownzp2024-01-22 07:28
    CodeRelease
  • Issue#3JianghaiSCU2023-12-26 10:04
    The restored results for IAGC and Diff-Retinex.
  • Issue comment#2ChunmingHe2023-12-16 03:46
    Code and pretrained models
  • Issue#1ChunmingHe2023-12-10 17:54
    你好,请问可以分享一下DiffIR、IAGC和Diff-Retinex 的增强结果图片吗,非常感谢
  • Issue#1ChunmingHe2023-12-10 17:26
    你好,请问可以分享一下DiffIR、IAGC和Diff-Retinex 的增强结果图片吗,非常感谢
  • Issue#1ChunmingHe2023-12-10 17:26
    你好,请问可以分享一下DiffIR、IAGC和Diff-Retinex 的增强结果图片吗,非常感谢
  • Issue#110139904242023-12-10 17:23
    你好,请问可以分享一下DiffIR和Diff-Retinex 的增强结果图片吗,非常感谢

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 56 stars here means stars gained during the window, not the repo's star count.