Skip to content

CIntellifusion/GeometryForcing

View on GitHub ↗Related repositories →

[ICLR26] Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

active 2025-07-092026-05-15 (UTC)

Partial coverage15,301 / 18,808 hourly files (81%) · 2 absent upstream · 3,506 failed, retryable2024-06-192026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
94
Pushes
4
Pull requests
0
Issues
7
Stars
59
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 311 days from 2025-07-09 to 2026-05-15. Pushes: 4 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 3 in a day. Comments: 21 total, peak 5 in a day. Stars: 59 total, peak 5 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
CIntellifusion174011
bobojiang264003
DrChiZhang4002
Hippogriff3003
ewrfcas1000
Riga21001
jiho3141001
Shuaizhang71000

Recent activity

Latest issues, pull requests and releases

  • Issue#16Shuaizhang72025-12-09 08:48
    Rotation 360 Video (16 Frames) Result
  • Issue comment#4CIntellifusion2025-12-02 03:13
    Some questions about the implementation details
  • Issue comment#14CIntellifusion2025-12-02 03:11
    Is the NFD project for Minecraft experiments open-sourced?
  • Issue comment#1CIntellifusion2025-11-26 02:56
    How to process the RealEstate10k dataset properly?
  • Issue comment#9Riga22025-11-09 09:36
    16 frames test
  • Issue comment#4jiho3142025-11-04 04:49
    Some questions about the implementation details
  • Issue comment#12CIntellifusion2025-10-21 10:09
    Details of RPE and RVE
  • Issue comment#10bobojiang262025-10-18 07:44
    How long does it take to train the model?
  • Issue comment#9CIntellifusion2025-10-17 03:58
    16 frames test
  • Issue comment#9Hippogriff2025-10-16 20:40
    16 frames test
  • Issue comment#9CIntellifusion2025-10-16 13:51
    16 frames test
  • Issue comment#6bobojiang262025-10-15 08:42
    Can you release the code for DINOV2 alignment loss which is showed in 'Main Results'?
  • Issue comment#6CIntellifusion2025-10-15 07:50
    Can you release the code for DINOV2 alignment loss which is showed in 'Main Results'?
  • Issue comment#11bobojiang262025-10-15 07:40
    Why would the training always start at epoch 21?
  • Issue comment#9CIntellifusion2025-10-15 04:10
    16 frames test
  • Issue#11CIntellifusion2025-10-15 04:05
    Why would the training always start at epoch 21?
  • Issue comment#11CIntellifusion2025-10-15 04:04
    Why would the training always start at epoch 21?
  • Issue comment#3CIntellifusion2025-10-05 04:13
    OOM error of training
  • Issue#4ewrfcas2025-10-03 12:29
    Some questions about the implementation details
  • Issue#3DrChiZhang2025-10-01 11:48
    OOM error of training
  • Issue comment#2DrChiZhang2025-10-01 10:00
    video generation with user input image
  • Issue#2DrChiZhang2025-10-01 10:00
    video generation with user input image
  • Issue comment#1CIntellifusion2025-10-01 07:50
    How to process the RealEstate10k dataset properly?
  • Issue#1CIntellifusion2025-10-01 07:50
    How to process the RealEstate10k dataset properly?
  • Issue comment#1Hippogriff2025-09-30 04:44
    How to process the RealEstate10k dataset properly?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 59 stars here means stars gained during the window, not the repo's star count.