<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Hi all, <br>
<br>
As part of the <b>CVPR 2023 workshop on Structural and
Compositional Learning on 3D Data (StruCo3D)</b> [<a
class="moz-txt-link-freetext"
href="https://struco3d.github.io/cvpr2023/">https://struco3d.github.io/cvpr2023/</a>],
we are organizing the
<b> BuildingNet challenge</b>. If you want to test your 3D
semantic segmentation/labeling algorithm on complex 3D point
clouds or meshes, feel free to participate! BuildingNet is a
publicly available large-scale dataset of annotated 3D building
models whose exteriors and surroundings are consistently labeled.
Buildings have more challenging structural complexity compared to
objects in existing 3D shape benchmarks, thus, there is currently
lots of room for improvement! <br>
<br>
More details here: <a class="moz-txt-link-freetext"
href="https://struco3d.github.io/cvpr2023/#challenge">https://struco3d.github.io/cvpr2023/#challenge</a>
(deadline for submitting your results is May 24)</p>
<p>Best wishes,<br>
CVPR '23 StruCo3D: BuildingNet challenge organizers (Marios
Loizou, Melinos Averkiou, Evangelos Kalogerakis)<br>
</p>
</body>
</html>