DejvaX commited on
Commit
9bafbd5
·
verified ·
1 Parent(s): 48283c5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -39,21 +39,21 @@ Because paired real damaged/complete crown data is scarce, the model was trained
39
 
40
  ### Checkpoints in this repository
41
 
42
- | File | Variant | Notes |
43
- |---|---|---|
44
- | `ToothCraft_normal_control_branch.pth` | Normal | Control-branch weights |
45
- | `ToothCraft_normal_diff_branch.pth` | Normal | Diffusion-branch weights |
46
- | `ToothCraft_classfree_control_branch.pth` | Classifier-free | Control-branch weights |
47
- | `ToothCraft_classfree_diff_branch.pth` | Classifier-free | Diffusion-branch weights |
48
- | `ToothCraft_antag_control_branch.pth` | Antagonist-aware | Control-branch weights |
49
- | `ToothCraft_antag_diff_branch.pth` | Antagonist-aware | Diffusion-branch weights |
50
- | `ToothCraft_gingiva-mod_control_branch.pth` | Gingiva-aware ⭐ | Control-branch weights |
51
- | `ToothCraft_gingiva-mod_diff_branch.pth` | Gingiva-aware ⭐ | Diffusion-branch weights |
52
 
53
- > **Note:** each of the variants ships a *control branch* and a *diffusion branch* checkpoint, which are loaded together at inference time. The
54
 
55
 
56
- > ⭐ **Recommended for clinical cases:** the gingiva-aware (`gingiva-mod`) variant reports improved results and is the best-suited checkpoint for real/clinical restorations.
57
  ## Usage
58
 
59
  Inference and training code, configuration files, and the data-augmentation pipeline are provided in the companion GitHub repository: [ikarus1211/VISAPP_ToothCraft](https://github.com/ikarus1211/VISAPP_ToothCraft). Download the checkpoint(s) for the variant you need from this repository and point the relevant config (e.g. `configs/test/test_normal.yaml`) at the local file paths, then run:
 
39
 
40
  ### Checkpoints in this repository
41
 
42
+ | File | Variant | Trained on | Notes |
43
+ |---|---|---|---|
44
+ | `ToothCraft_normal_control_branch.pth` | Normal | ODD | Control-branch weights |
45
+ | `ToothCraft_normal_diff_branch.pth` | Normal | ODD | Diffusion-branch weights |
46
+ | `ToothCraft_classfree_control_branch.pth` | Classifier-free | ODD | Control-branch weights |
47
+ | `ToothCraft_classfree_diff_branch.pth` | Classifier-free | ODD | Diffusion-branch weights |
48
+ | `ToothCraft_antag_control_branch.pth` | Antagonist-aware | ODD | Control-branch weights |
49
+ | `ToothCraft_antag_diff_branch.pth` | Antagonist-aware | ODD | Diffusion-branch weights |
50
+ | `ToothCraft_gingiva-mod_control_branch.pth` | Gingiva-aware ⭐ | ODD | Control-branch weights |
51
+ | `ToothCraft_gingiva-mod_diff_branch.pth` | Gingiva-aware ⭐ | ODD | Diffusion-branch weights |
52
 
53
+ > **Note:** each of the variants ships a *control branch* and a *diffusion branch* checkpoint, which are loaded together at inference time.
54
 
55
 
56
+ > ⭐ **Recommended for clinical cases:** the gingiva-aware (`gingiva-mod`) variant reports improved results and is the best-suited checkpoint for real/clinical restorations, where the tooth does not properly connect to gingiva.
57
  ## Usage
58
 
59
  Inference and training code, configuration files, and the data-augmentation pipeline are provided in the companion GitHub repository: [ikarus1211/VISAPP_ToothCraft](https://github.com/ikarus1211/VISAPP_ToothCraft). Download the checkpoint(s) for the variant you need from this repository and point the relevant config (e.g. `configs/test/test_normal.yaml`) at the local file paths, then run: