Skip to content

facebookresearch/holo_diffusion

View on GitHub ↗Related repositories →

Code repository for the CVPR2023 publication "HoloDiffusion: Training a 3D diffusion model using 2D Images"

active 2023-08-172025-05-24 (UTC)

Complete coverage26,494 / 26,494 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
115
Pushes
1
Pull requests
0
Issues
8
Stars
94
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 647 days from 2023-08-17 to 2025-05-24. Pushes: 1 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 3 in a day. Comments: 7 total, peak 2 in a day. Stars: 94 total, peak 7 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
akanimax8106
yuedajiong3000
00lihao1000
hanabi71000
Mu-Yanchen1000
lai01988488811001
MohamedKHALILRouissi1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#11akanimax2024-06-17 08:07
    Questions about strange results
  • Issue#11Mu-Yanchen2024-06-13 07:48
    Questions about strange results
  • Issue#10yuedajiong2024-02-25 05:56
    how to understand this innovation: ”an image formation model that decouples model memory from spatial memory“
  • Issue#9yuedajiong2024-02-25 05:49
    Is there any plan to ...
  • Issue#8yuedajiong2024-02-25 05:15
    What is the better/suitable 3D representation in 3D/4D generation?
  • Issue comment#5akanimax2024-01-15 21:53
    Can you provide the code for quantitative evaluation?
  • Issue comment#7akanimax2024-01-15 21:53
    is it possible to use multiple 2d images of room and reconstruct the mesh model ?
  • Issue#7akanimax2024-01-15 21:53
    is it possible to use multiple 2d images of room and reconstruct the mesh model ?
  • Issue#7MohamedKHALILRouissi2023-12-20 13:15
    is it possible to use multiple 2d images of room and reconstruct the mesh model ?
  • Issue#6hanabi72023-12-12 09:48
    trained checkpoint
  • Issue comment#5akanimax2023-11-24 22:20
    Can you provide the code for quantitative evaluation?
  • Issue#500lihao2023-11-21 13:01
    Can you provide the code for quantitative evaluation?
  • Issue comment#4akanimax2023-08-20 11:50
    Problem of training settings
  • Issue comment#4lai01988488812023-08-19 10:15
    Problem of training settings
  • Issue comment#4akanimax2023-08-17 19:52
    Problem of training settings

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 94 stars here means stars gained during the window, not the repo's star count.