You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,6 +16,8 @@ You can directly download our test results from Google Drive: (1) [PCDMs vs SOTA
16
16
The [PCDMs vs SOTA](https://drive.google.com/drive/folders/1q21tA3VsQqScecQ7m3_eUFxIPWUGYKAa?usp=drive_link) compares our method with several state-of-the-art methods e.g. ADGAN, PISE, GFLA, DPTN, CASD, NTED, PIDM.
17
17
Each row contains target_pose, source_image, ground_truth, ADGAN, PISE, GFLA, DPTN, CASD, NTED, PIDM, and PCDMs (ours) respectively.
18
18
19
+
20
+
We present a simplified version of PCDMs and only use stage2, utilizing training data from TikTok and DeepFashion.
19
21
The weights can be obtained from [Google drive](https://drive.google.com/drive/folders/1hnPm-GzaAtQKjgG_glhlQZieJ5g5Xd-y?usp=drive_link).
20
22
21
23
Download dwpose weights (`dw-ll_ucoco_384.pth`, `yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth`) following [this](https://github.com/IDEA-Research/DWPose?tab=readme-ov-file#-dwpose-for-controlnet).
0 commit comments