Skip to content

DepthAnything/Depth-Anything-V2

View on GitHub ↗Related repositories →

深度学习深度相机深度标定

Python · active 2025-03-272026-08-08 (UTC)

Partial coverage11,277 / 12,038 hourly files (94%) · 2 absent upstream · 758 failed, retryable2025-03-272026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.6K
Pushes
1
Pull requests
4
Issues
25
Stars
1.3K
Forks
157

Activity over time

Daily event counts in the loaded window

Line chart, 500 days from 2025-03-27 to 2026-08-08. Pushes: 1 total, peak 1 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 25 total, peak 2 in a day. Comments: 60 total, peak 3 in a day. Stars: 1,309 total, peak 15 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#308Yunxiang-Wang2026-01-20 02:12
    output metric depth compare with LiDAR data
  • Issue#315ZoengMingWong2026-01-19 07:51
    Depth for pseudo-labeled images with privacy blurred faces
  • Pull request#314Degior2026-01-13 21:55
  • Issue comment#312gururajbg2026-01-04 13:40
    xFormers not available → model imports OK, but infer_image returns all-zero depth map (min=0.0, max=0.0)
  • Issue comment#313muses02292025-12-13 02:07
    Depth-Anything-V2-Giant
  • Issue comment#313heyoeyo2025-12-12 14:55
    Depth-Anything-V2-Giant
  • Issue#312Wasiq11232025-12-06 18:31
    xFormers not available → model imports OK, but infer_image returns all-zero depth map (min=0.0, max=0.0)
  • Issue comment#310Wasiq11232025-12-06 18:28
    xFormers memory-efficient attention not supported on CPU
  • Issue comment#310heyoeyo2025-12-05 21:04
    xFormers memory-efficient attention not supported on CPU
  • Issue comment#208reazmoj2025-11-30 00:53
    train
  • Issue comment#69reazmoj2025-11-30 00:49
    what min_depth and max_depth values to use for relative depth
  • Issue comment#233reazmoj2025-11-30 00:24
    train relative depth
  • Issue#309az45uhuj2025-11-26 12:16
    Outdoor (VKITTI) model produces incorrect depth when max_depth=80, but works when max_depth=20
  • Issue comment#81codimahi2025-11-26 04:31
    Clarification needed on licensing
  • Issue comment#307niyeee42025-11-13 06:05
    How can I use Depth Anything on Android?
  • Issue comment#89vitoraugustx2025-11-04 23:25
    Updated metric depth to point cloud code
  • Issue comment#178vitoraugustx2025-11-04 22:46
    How to extract depth value in meters from the depth map?
  • Issue#302AxxhimK932025-10-29 07:51
    Region of Interest for endoscopic videos
  • Issue#307BaoAn212025-10-29 02:41
    How can I use Depth Anything on Android?
  • Issue#306rustoys377-sys2025-10-26 12:39
    Tutorial for Installation
  • Issue comment#305heyoeyo2025-10-24 19:49
    关于深度倒装的问题
  • Issue comment#305Yang-Xijie2025-10-24 15:30
    关于深度倒装的问题
  • Issue#305ZhengDonglei2025-10-23 09:13
    关于深度倒装的问题
  • Issue#302AxxhimK932025-10-08 15:24
    Region of Interest for endoscopic videos
  • Issue comment#95CloudsRL2025-10-03 14:57
    About the true scale

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,309 stars here means stars gained during the window, not the repo's star count.