Skip to content

Pointcept/PointTransformerV3

View on GitHub ↗Related repositories →

[CVPR'24 Oral] Use VQVAE with Point Transformer to generate point cloud

active 2023-12-172026-07-02 (UTC)

Partial coverage20,502 / 26,258 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.3K
Pushes
18
Pull requests
0
Issues
108
Stars
879
Forks
52

Activity over time

Daily event counts in the loaded window

Line chart, 929 days from 2023-12-17 to 2026-07-02. Pushes: 18 total, peak 5 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 108 total, peak 5 in a day. Comments: 285 total, peak 22 in a day. Stars: 879 total, peak 45 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#179Gofinge2025-12-30 12:13
    Difference between released nuScenes results and leaderboard score
  • Issue#179stttw2025-12-18 08:56
    Difference between released nuScenes results and leaderboard score
  • Issue#178L-Reichardt2025-12-17 21:46
    Paper Question
  • Issue comment#178Gofinge2025-12-17 21:13
    Paper Question
  • Issue#178L-Reichardt2025-12-13 14:49
    Paper Question
  • Issue comment#163Gofinge2025-12-03 08:29
    Are model weights available now after model fix?
  • Issue#169Prism-hua2025-11-30 07:41
    Training time consuming on S3DIS
  • Issue comment#171Gofinge2025-11-30 02:18
    custom head for PTV3 semantic segmentation
  • Issue comment#176Kevinpyx2025-11-08 08:38
    all_profile_res.empty() assert faild. can't find suitable algorithm for 0
  • Issue comment#173tim-kuechler2025-10-22 08:39
    Why still use BatchNorm for spconv(embedding) and Pool/UnPool?
  • Issue comment#170aadith-warrier2025-10-05 18:25
    NuScenes val mIoU ≈ 4.9%
  • Issue#171naisarg-pandya2025-09-30 10:19
    custom head for PTV3 semantic segmentation
  • Issue#169Prism-hua2025-09-23 02:50
    Training time consuming on S3DIS
  • Issue comment#168yt26392025-09-12 21:17
    Results change during testing / evaluation
  • Issue#168yt26392025-09-12 21:17
    Results change during testing / evaluation
  • Issue comment#168Gofinge2025-09-12 17:21
    Results change during testing / evaluation
  • Issue comment#167wazzysky2025-08-15 06:20
    how to visualize the model PTv3
  • Issue comment#167Gofinge2025-08-12 14:44
    how to visualize the model PTv3
  • Issue#167wazzysky2025-08-12 06:24
    how to visualize the model PTv3
  • Issue comment#165alinlyx2025-08-06 17:45
    why the total_steps is 0 ?
  • Issue comment#165Gofinge2025-08-06 11:54
    why the total_steps is 0 ?
  • Issue comment#164Gofinge2025-08-05 20:18
    Can this model be used for Point Cloud Video
  • Issue comment#159kenomo2025-08-05 18:25
    SparseConv is blocking PTV3 from running on CUDA 12.8/Blackwell GPUs (5070, 5080, RTX Pro 6000)
  • Issue#163Zifeng-Zhang2025-07-31 04:47
    Are model weights available now after model fix?
  • Issue#161juliuskuehn12025-07-28 08:38
    FileNotFoundError when training PointFormer V3 - Missing nuscenes_infos_10sweeps_train.pkl

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 879 stars here means stars gained during the window, not the repo's star count.