Skip to content

view

Otakar Jašek
presents
Dynamic Graph CNN for Learning on Point Clouds
 
On 2019-03-26 10:30 at G205
 
Reading group on the work by Y. Wang, Y. Sun, Z. Liu, S. Sarma, M. Bronstein,
J.
Solomon, in arxiv 2018. Presented by Jasek Otakar.

Paper abstract: Point clouds provide a flexible and scalable geometric
representation suitable for countless applications in computer graphics; they
also comprise the raw output of most 3D data acquisition devices. Hence, the
design of intelligent computational models that act directly on point clouds is
critical, especially when efficiency considerations or noise preclude the
possibility of expensive denoising and meshing procedures. While hand-designed
features on point clouds have long been proposed in graphics and vision,
however, the recent overwhelming success of convolutional neural networks
(CNNs)
for image analysis suggests the value of adapting insight from CNN to the point
cloud world. To this end, we propose a new neural network module dubbed
EdgeConv
suitable for CNN-based high-level tasks on point clouds including
classification
and segmentation. EdgeConv is differentiable and can be plugged into existing
architectures. Compared to existing modules operating largely in extrinsic
space
or treating each point independently, EdgeConv has several appealing
properties:
It incorporates local neighborhood information; it can be stacked or
recurrently
applied to learn global shape properties; and in multi-layer systems affinity
in
feature space captures semantic characteristics over potentially long distances
in the original embedding. Beyond proposing this module, we provide extensive
evaluation and analysis revealing that EdgeConv captures and exploits
fine-grained geometric properties of point clouds. The proposed approach
achieves state-of-the-art performance on standard benchmarks including
ModelNet40 and S3DIS.

Paper URL: https://arxiv.org/pdf/1801.07829.pdf

Reading group participants: Preferably, send questions about the unclear parts
to the speaker at least one day in advance.

See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html
Back to the list