Skip to content

[T-PAMI 2025] DiffMVS & CasDiffMVS

active 2025-08-112026-05-17 (UTC)

Partial coverage13,414 / 15,996 hourly files (84%) · 2 absent upstream · 2,576 failed, retryable2024-10-132026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
101
Pushes
3
Pull requests
0
Issues
8
Stars
79
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 280 days from 2025-08-11 to 2026-05-17. Pushes: 3 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 2 in a day. Comments: 5 total, peak 1 in a day. Stars: 79 total, peak 17 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
FangjinhuaWang9304
reynoldscem-oculo2000
wsh10571000
wsh07111001
lihahaya1231000
NielsRogge1000
ashimdahal1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#11FangjinhuaWang2026-03-07 03:23
    The loss cost is negative
  • Issue comment#10FangjinhuaWang2026-01-20 02:10
    Why is it necessary to use preprocessed depth maps for training on the DTU dataset?
  • Issue#9wsh10572026-01-16 04:10
    How to perform dense reconstruction using DiffMVS?
  • Issue comment#9wsh07112026-01-07 08:29
    How to perform dense reconstruction using DiffMVS?
  • Issue#7FangjinhuaWang2025-10-19 15:16
    1/ depth for disp and 1/ disp for depth
  • Issue#7lihahaya1232025-10-17 15:33
    1/ depth for disp and 1/ disp for depth
  • Issue comment#6FangjinhuaWang2025-10-17 09:31
    If the pre-trained model can be directly transferred to images of different resolutions
  • Issue#5ashimdahal2025-09-27 03:38
    Do you plan to release onnx or tensorrt versions of the code for real time application?
  • Issue#4NielsRogge2025-09-19 12:29
    Release DiffMVS and CasDiffMVS models on Hugging Face
  • Issue#3FangjinhuaWang2025-09-05 06:32
    Comparison to MVSFormer++
  • Issue comment#1FangjinhuaWang2025-09-05 06:31
    Comparison to MVSFormer++
  • Issue#3reynoldscem-oculo2025-09-04 16:33
    Comparison to MVSFormer++
  • Issue#1reynoldscem-oculo2025-09-04 16:29
    Comparison to MVSFormer++

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 79 stars here means stars gained during the window, not the repo's star count.