Skip to content

[T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

active 2024-09-102026-06-29 (UTC)

Partial coverage14,008 / 16,813 hourly files (83%) · 2 absent upstream · 2,804 failed, retryable2024-09-092026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
70
Pushes
1
Pull requests
0
Issues
14
Stars
32
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 658 days from 2024-09-10 to 2026-06-29. Pushes: 1 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 2 in a day. Comments: 21 total, peak 9 in a day. Stars: 32 total, peak 1 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
HaoyiZhu211012
qiuzidian6003
RayYoh5004
NielsRogge2002
RobinLiuZX1000
Yummy1989131000

Recent activity

Latest issues, pull requests and releases

  • Issue#31HaoyiZhu2025-11-17 02:12
    For the object point cloud
  • Issue comment#29NielsRogge2025-09-30 06:40
    Release PonderV2 checkpoints on Hugging Face
  • Issue comment#29NielsRogge2025-09-29 12:34
    Release PonderV2 checkpoints on Hugging Face
  • Issue#29HaoyiZhu2025-09-29 11:18
    Release PonderV2 checkpoints on Hugging Face
  • Issue#30HaoyiZhu2025-09-29 11:18
    About the use of pre-trained models
  • Issue comment#30HaoyiZhu2025-06-12 07:38
    About the use of pre-trained models
  • Issue#28Yummy1989132025-04-16 02:51
    About the pretrain-finetune setup
  • Issue comment#26qiuzidian2025-01-19 10:25
    question about input of spconv_unet_v1m3_pdnorm
  • Issue#26qiuzidian2025-01-19 10:25
    question about input of spconv_unet_v1m3_pdnorm
  • Issue comment#26HaoyiZhu2025-01-19 10:09
    question about input of spconv_unet_v1m3_pdnorm
  • Issue comment#26qiuzidian2025-01-18 13:11
    question about input of spconv_unet_v1m3_pdnorm
  • Issue#26qiuzidian2025-01-18 13:11
    question about input of spconv_unet_v1m3_pdnorm
  • Issue comment#26qiuzidian2025-01-18 13:05
    question about input of spconv_unet_v1m3_pdnorm
  • Issue#26qiuzidian2025-01-18 13:05
    question about input of spconv_unet_v1m3_pdnorm
  • Issue comment#26HaoyiZhu2025-01-18 09:17
    question about input of spconv_unet_v1m3_pdnorm
  • Issue#23HaoyiZhu2025-01-05 15:16
    Unsupervised Pre-training Results
  • Issue#24HaoyiZhu2025-01-05 15:16
    I encountered a question when preprocessing the structured3d dataset
  • Issue comment#25RayYoh2024-12-17 06:35
    Inquiry about the preprocess of ScanNet
  • Issue#25RayYoh2024-12-17 06:35
    Inquiry about the preprocess of ScanNet
  • Issue comment#25HaoyiZhu2024-12-17 02:48
    Inquiry about the preprocess of ScanNet
  • Issue comment#25RayYoh2024-12-14 10:32
    Inquiry about the preprocess of ScanNet
  • Issue comment#25HaoyiZhu2024-12-14 07:24
    Inquiry about the preprocess of ScanNet
  • Issue comment#25HaoyiZhu2024-12-13 07:45
    Inquiry about the preprocess of ScanNet
  • Issue comment#25RayYoh2024-12-13 07:29
    Inquiry about the preprocess of ScanNet
  • Issue comment#25HaoyiZhu2024-12-13 07:05
    Inquiry about the preprocess of ScanNet

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 32 stars here means stars gained during the window, not the repo's star count.