upload apple example

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.JPG filter=lfs diff=lfs merge=lfs -text
 *.mp4 filter=lfs diff=lfs merge=lfs -text
+vggsfm_code/examples/ filter=lfs diff=lfs merge=lfs -text

app.py

@@ -203,8 +203,9 @@ with gr.Blocks() as demo:
         <li>upload the images (.jpg, .png, etc.), or </li> 
         <li>upload a video (.mp4, .mov, etc.) </li> 
     </ul> 
-    <p>The reconstruction should normally take <strong> up to 90 second </strong>. If both images and videos are uploaded, the demo will only reconstruct the uploaded images. By default, we extract <strong> 1 image frame per second from the input video </strong>. To prevent crashes on the Hugging Face space, we currently limit reconstruction to the first 20 image frames. </p> 
+    <p>If both images and videos are uploaded, the demo will only reconstruct the uploaded images. By default, we extract <strong> 1 image frame per second from the input video </strong>. To prevent crashes on the Hugging Face space, we currently limit reconstruction to the first 20 image frames. </p> 
     <p>SfM methods are designed for <strong> rigid/static reconstruction </strong>. When dealing with dynamic/moving inputs, these methods may still work by focusing on the rigid parts of the scene. However, to ensure high-quality results, it is better to minimize the presence of moving objects in the input data. </p> 
+    <p>The reconstruction should typically take up to 90 seconds. If it takes longer, the input data is likely not well-conditioned. </p> 
     <p>If you meet any problem, feel free to create an issue in our <a href="https://github.com/facebookresearch/vggsfm" target="_blank">GitHub Repo</a> ⭐</p> 
     <p>(Please note that running reconstruction on Hugging Face space is slower than on a local machine.) </p> 
     </div>
@@ -216,7 +217,7 @@ with gr.Blocks() as demo:
             input_images = gr.File(file_count="multiple", label="Input Images", interactive=True)
             num_query_images = gr.Slider(minimum=1, maximum=10, step=1, value=5, label="Number of query images (key frames)",
                                          info="More query images usually lead to better reconstruction at lower speeds. If the viewpoint differences between your images are minimal, you can set this value to 1. ")
-            num_query_points = gr.Slider(minimum=512, maximum=4096, step=1, value=1024, label="Number of query points",
+            num_query_points = gr.Slider(minimum=512, maximum=3072, step=1, value=1024, label="Number of query points",
                                          info="More query points usually lead to denser reconstruction at lower speeds.")
         
         with gr.Column(scale=3):

images_to_videos.py

@@ -2,7 +2,7 @@ import cv2
 import os
 
 # Parameters
-name = "bonsai"
+name = "apple"
 folder_path = f'vggsfm_code/examples/{name}/images'  # Update with the path to your images
 video_path = f'vggsfm_code/examples/videos/{name}_video.mp4'
 fps = 1  # frames per second

vggsfm_code/examples/videos/apple_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a7f05247a574e0f77926345bb68a3b3c9044adcd6c6432c25f7e2ccc38b38b
+size 1846808