oyiya commited on
Commit
322d107
·
verified ·
1 Parent(s): c4950bb

modify model card

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -16,23 +16,23 @@ This repository hosts the pretrained parameters for the SuperMat project, as des
16
 
17
  | Model | Description |
18
  | --- | --- |
19
- | supermat.ckpt | Base SuperMat model for material decomposition
20
- | supermat_mv.ckpt | Multi-view version of SuperMat processing six orthogonal views
21
- | uv_refine_bc | UV refinement network for albedo materials
22
- | uv_refine_rm | UV refinement network for roughness & metallic materials
23
 
24
  All models are built upon the base model `stabilityai/stable-diffusion-2-1`.
25
  Note: The official `stabilityai/stable-diffusion-2-1` model has been removed. You may need to obtain the base model parameters through alternative sources, such as `sd2-community/stable-diffusion-2-1`.
26
 
27
  # Model Details
28
- #### SuperMat (supermat.ckpt)
29
  The core model for material decomposition. It takes RGBA images as input and decomposes materials from the target object.
30
- #### SuperMat Multi-View (supermat_mv.ckpt)
31
  An extended version that processes six orthogonal views simultaneously. This model leverages multi-view consistency for improved material estimation. For each view, the camera-to-world (c2w) matrix is provided as camera embeddings.
32
  #### UV Refinement Networks
33
  Two specialized networks for refining UV maps:
34
- - uv_refine_bc: Refines the UV map for albedo materials
35
- - uv_refine_rm: Refines the UV map for roughness & metallic materials
36
 
37
  # Download & Usage
38
  Download the desired model(s) from this repository and place them in the checkpoints folder:
 
16
 
17
  | Model | Description |
18
  | --- | --- |
19
+ | supermat.pth | Base SuperMat model for material decomposition
20
+ | supermat_mv.pth | Multi-view version of SuperMat processing six orthogonal views
21
+ | uv_refine_bc.pth | UV refinement network for albedo materials
22
+ | uv_refine_rm.pth | UV refinement network for roughness & metallic materials
23
 
24
  All models are built upon the base model `stabilityai/stable-diffusion-2-1`.
25
  Note: The official `stabilityai/stable-diffusion-2-1` model has been removed. You may need to obtain the base model parameters through alternative sources, such as `sd2-community/stable-diffusion-2-1`.
26
 
27
  # Model Details
28
+ #### SuperMat (supermat.pth)
29
  The core model for material decomposition. It takes RGBA images as input and decomposes materials from the target object.
30
+ #### SuperMat Multi-View (supermat_mv.pth)
31
  An extended version that processes six orthogonal views simultaneously. This model leverages multi-view consistency for improved material estimation. For each view, the camera-to-world (c2w) matrix is provided as camera embeddings.
32
  #### UV Refinement Networks
33
  Two specialized networks for refining UV maps:
34
+ - uv_refine_bc.pth: Refines the UV map for albedo materials
35
+ - uv_refine_rm.pth: Refines the UV map for roughness & metallic materials
36
 
37
  # Download & Usage
38
  Download the desired model(s) from this repository and place them in the checkpoints folder: