Yiwen-ntu commited on
Commit
c44fe06
1 Parent(s): c95d1ba

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -199,8 +199,9 @@ For text/image to Artist-Created Mesh. We suggest first using <a href='https://h
199
  Code: <a href='https://github.com/buaacyw/MeshAnythingV2' target='_blank'>GitHub</a>. Arxiv Paper: <a href='https://arxiv.org/abs/2406.10163' target='_blank'>ArXiv</a>.
200
 
201
  ❗️❗️❗️**Important Notes:**
 
202
  - Gradio doesn't support interactive wireframe rendering currently. For interactive mesh visualization, please use download the obj file and open it with MeshLab or https://3dviewer.net/.
203
- - The input mesh will be normalized to a unit bounding box. The up vector of the input mesh should be +Y for better results. Click **Preprocess with Marching Cubes** if the input mesh is a manually created mesh.
204
  - Limited by computational resources, MeshAnything is trained on meshes with fewer than 1600 faces and cannot generate meshes with more than 1600 faces. The shape of the input mesh should be sharp enough; otherwise, it will be challenging to represent it with only 1600 faces. Thus, feed-forward image-to-3D methods may often produce bad results due to insufficient shape quality.
205
  - For point cloud input, please refer to our github repo <a href='https://github.com/buaacyw/MeshAnythingV2' target='_blank'>GitHub</a>.
206
  '''
 
199
  Code: <a href='https://github.com/buaacyw/MeshAnythingV2' target='_blank'>GitHub</a>. Arxiv Paper: <a href='https://arxiv.org/abs/2406.10163' target='_blank'>ArXiv</a>.
200
 
201
  ❗️❗️❗️**Important Notes:**
202
+ - Please Click on **Preprocess with Marching Cubes** if the input mesh is not produced by Marching Cubes.
203
  - Gradio doesn't support interactive wireframe rendering currently. For interactive mesh visualization, please use download the obj file and open it with MeshLab or https://3dviewer.net/.
204
+ - The input mesh will be normalized to a unit bounding box. The up vector of the input mesh should be +Y for better results.
205
  - Limited by computational resources, MeshAnything is trained on meshes with fewer than 1600 faces and cannot generate meshes with more than 1600 faces. The shape of the input mesh should be sharp enough; otherwise, it will be challenging to represent it with only 1600 faces. Thus, feed-forward image-to-3D methods may often produce bad results due to insufficient shape quality.
206
  - For point cloud input, please refer to our github repo <a href='https://github.com/buaacyw/MeshAnythingV2' target='_blank'>GitHub</a>.
207
  '''