Skip to content

Commit

Permalink
Merge pull request #100 from IRVLUTD/HOCap
Browse files Browse the repository at this point in the history
add object shape reconstruction
  • Loading branch information
yuxng authored Jun 18, 2024
2 parents 7fb9c8e + 1cdbd5f commit e4f22f9
Show file tree
Hide file tree
Showing 2 changed files with 22 additions and 10 deletions.
Binary file added HOCap/assets/images/object_shape.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
32 changes: 22 additions & 10 deletions HOCap/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -177,27 +177,39 @@ <h3>Abstract</h3>
</div>

<div class="section">
<h3>Data Capture Setup</h3>
<h3>Data Capture Setup (9 RGB-D Cameras + HoloLens, No Mo-cap)</h3>
<div class="center pipeline">
<img src="./assets/images/hardware.png" alt="Hardware Image" />
</div>
</div>

<div class="section">
<h3>Annotation Pipeline</h3>
<div class="center pipeline">
<img src="./assets/images/pipeline.png" alt="Pipeline Image" />
</div>
</div>

<div class="section">
<h3>Reconstructed Object Shapes</h3>
<h3>Object Shape Reconstruction using a Single Azure Camera</h3>
<div class="center pipeline">
<img
src="./assets/images/object_shape.png"
alt="Object Shape"
/>
</div>
<br />
<div class="center pipeline">
<img
src="./assets/images/object-shapes.png"
alt="Object Shapes"
/>
</div>
</div>

<div class="section">
<h3>Semi-automatic Annotation Pipeline for Hand-Object Poses</h3>
<p> The only human annotation required is to manually prompt
two points for each object in the first frame to generate an initial segmentation
mask of the object using SAM, and label the name of the object to associate
it to an object in our database.
</p>
<div class="center pipeline">
<img src="./assets/images/pipeline.png" alt="Pipeline Image" />
</div>
</div>

<div class="section">
Expand Down

0 comments on commit e4f22f9

Please sign in to comment.