个人调整版[CVPR 2024 Highlight] Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
active 2023-10-30 → 2025-11-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 745 days from 2023-10-30 to 2025-11-12. Pushes: 17 total, peak 2 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 72 total, peak 8 in a day. Comments: 115 total, peak 10 in a day. Stars: 169 total, peak 4 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Windsrain | 98 | 17 | 1 | 60 |
| Guptajakala | 17 | 0 | 0 | 9 |
| S1aoXuan | 11 | 0 | 0 | 10 |
| lsyl20 | 9 | 0 | 0 | 5 |
| MSH970515 | 9 | 0 | 0 | 5 |
| iaphantom | 5 | 0 | 0 | 1 |
| name-liang | 5 | 0 | 0 | 3 |
| sol924 | 5 | 0 | 0 | 3 |
| zjyaccount | 3 | 0 | 0 | 1 |
| naik24 | 3 | 0 | 0 | 1 |
| JarvisLee0423 | 3 | 0 | 0 | 1 |
| a162837 | 3 | 0 | 0 | 2 |
| hihxy | 3 | 0 | 0 | 1 |
| dinaabdelhalim | 3 | 0 | 0 | 1 |
| zhangjy328 | 2 | 0 | 0 | 1 |
| warren-wzw | 2 | 0 | 0 | 2 |
| drilistbox | 2 | 0 | 0 | 1 |
| autodriving-heart | 2 | 0 | 0 | 1 |
| Elenairene | 2 | 0 | 0 | 1 |
| starzero-hhh | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#41C-H-Chien2025-11-12 04:39Questions about quantitative evaluation on the edge areas
- Issue#41C-H-Chien2025-11-11 20:07Questions about quantitative evaluation on the edge areas
- Issue comment#40lsyl202025-08-18 01:25Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue#40lsyl202025-08-18 01:25Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue comment#40Windsrain2025-08-17 12:45Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue comment#40lsyl202025-08-08 05:13Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue#40lsyl202025-08-08 05:13Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue comment#40Windsrain2025-08-08 05:01Issue with invalid ground truth in TEST/A/0149/left/0015.png on SceneFlow dataset
- Issue comment#39dinaabdelhalim2025-07-15 16:17old versions of pretrained models. Checkpoint state_dict keys differ from RAFT keys.
- Issue#39dinaabdelhalim2025-07-15 16:17old versions of pretrained models. Checkpoint state_dict keys differ from RAFT keys.
- Issue#39dinaabdelhalim2025-07-15 09:04old versions of pretrained models. Checkpoint state_dict keys differ from RAFT keys.
- Issue#35Windsrain2025-06-27 07:53RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.
- Issue comment#37Windsrain2025-06-27 07:52The usage of freeze_bn
- Issue#37Windsrain2025-06-27 07:52The usage of freeze_bn
- Issue#38Windsrain2025-06-27 07:51selective-IGEV
- Issue comment#38Windsrain2025-06-19 13:11selective-IGEV
- Issue#36Windsrain2025-03-21 05:56有关训练的问题
- Issue comment#36a1628372025-03-20 08:09有关训练的问题
- Issue comment#36Windsrain2025-03-20 08:07有关训练的问题
- Issue comment#36a1628372025-03-20 08:05有关训练的问题
- Issue comment#36Windsrain2025-03-20 08:00有关训练的问题
- Issue#36a1628372025-03-20 07:47有关训练的问题
- Issue#28Windsrain2025-03-11 06:07模型推理时间的疑问
- Issue#33Windsrain2025-03-11 06:07Selective-RAFT Middlebury weights
- Issue#34Windsrain2025-03-11 06:07模型选择
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 169 stars here means stars gained during the window, not the repo's star count.