Skip to content

[3DV 2025, Oral] LoopSplat: Loop Closure by Registering 3D Gaussian Splats

active 2024-08-202026-05-31 (UTC)

Partial coverage17,772 / 22,831 hourly files (78%) · 2 absent upstream · 5,058 failed, retryable2024-01-042026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
291
Pushes
5
Pull requests
0
Issues
26
Stars
214
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 650 days from 2024-08-20 to 2026-05-31. Pushes: 5 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 26 total, peak 4 in a day. Comments: 35 total, peak 4 in a day. Stars: 214 total, peak 24 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

Recent activity

Latest issues, pull requests and releases

  • Issue comment#35Zhu-Liyuan2025-10-05 17:20
    Is this an enhanced reconstruction rendering, and can SLAM information be used as input?
  • Issue#35Zhu-Liyuan2025-10-05 17:20
    Is this an enhanced reconstruction rendering, and can SLAM information be used as input?
  • Issue#33Zhu-Liyuan2025-08-15 15:03
    Tracking Loss
  • Issue#34BW-Zhang052025-08-15 12:48
    Something wrong in ScanNet 0059
  • Issue comment#34Zhu-Liyuan2025-08-13 16:44
    Something wrong in ScanNet 0059
  • Issue comment#34Zhu-Liyuan2025-08-13 16:32
    Something wrong in ScanNet 0059
  • Issue#34BW-Zhang052025-08-13 12:35
    Something wrong in ScanNet 0059
  • Issue comment#33Zhu-Liyuan2025-07-31 16:20
    Tracking Loss
  • Issue comment#33Anniebhalla162025-07-30 08:19
    Tracking Loss
  • Issue#33Anniebhalla162025-07-25 11:30
    Tracking Loss
  • Issue comment#32homocysteine2025-07-17 03:55
    When using GT poses, the rendering quality seems to worsen.
  • Issue comment#22zuoweic2025-07-09 02:35
    Faiss assertion Error
  • Issue#31xiaobozhou-study2025-06-29 12:29
    download of NetVLAD
  • Issue#28Zhu-Liyuan2025-06-20 20:54
    python-pycg version
  • Issue comment#26Zhu-Liyuan2025-06-08 20:25
    LooSplat on outdoor dataset
  • Issue#26Zhu-Liyuan2025-06-08 20:25
    LooSplat on outdoor dataset
  • Issue comment#27Zhu-Liyuan2025-06-04 20:07
    Online GS viwer support?
  • Issue#27Zhu-Liyuan2025-06-04 20:07
    Online GS viwer support?
  • Issue comment#24lemonci2025-05-17 18:43
    Why are the transformations for the odometry edges set to identity matrix?
  • Issue#24lemonci2025-05-17 18:43
    Why are the transformations for the odometry edges set to identity matrix?
  • Issue comment#24lemonci2025-05-10 01:51
    Why are the transformations for the odometry edges set to identity matrix?
  • Issue comment#25Anniebhalla162025-05-04 16:18
    Error running LoopSplat
  • Issue comment#24lemonci2025-04-30 01:24
    Why are the transformations for the odometry edges set to identity matrix?
  • Issue comment#24Zhu-Liyuan2025-04-30 01:04
    Why are the transformations for the odometry edges set to identity matrix?
  • Issue comment#24lemonci2025-04-30 01:00
    Why are the transformations for the odometry edges set to identity matrix?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 214 stars here means stars gained during the window, not the repo's star count.