Neural Geometry Processing
Tatsuya Yatagawa
Aug. 27th, 2022
SIGGRAPH 2022 Paper Reading Seminar
Slide 2
Slide 2 text
6 TOG , 2 Conference Track
l Dual Octree Graph Networks for Learning Adaptive Volumetric ...
l DiffusionNet: Discretization Agnostic Learning on Surfaces
l Neural Dual Contouring
l Random Walks for Adversarial Meshes
l PCEDNet: A Lightweight Neural Network for Fast and Interactive ...
l Self-Sampling for Neural Point Cloud Consolidation
l ImLoveNet: Misalignment Image-supported Registration Network ...
l DSG-Net: Learning Disentangled Structure and Geometry ...
Neural Geometry Processing (8 papers)
ImLoveNet: Misaligned Image-supported Registration Network
for Low-overlap Point Cloud Pairs (Conf. Track)
2
Slide 26
Slide 26 text
: , 2
l (DGR [Choy+ 2020],
PREDATOR [Huang+ 2021] etc.).
l
)
Slide 27
Slide 27 text
SOTA (PREDATOR, OMNet)
: ,
,
.
Slide 28
Slide 28 text
DSG-Net: Learning Disentangled Structure and
Geometry for 3D Shape Generation
(VAE)
Slide 29
Slide 29 text
:
,
.
:
.
Slide 30
Slide 30 text
l 2
+
( ) ( )
l as-consistent-as-
possible (9
BBox ) [Guo+ 2019]
l one-hot
MLP
l ACAP BBox
,
.
Slide 31
Slide 31 text
(SDM-Net) , ,
Slide 32
Slide 32 text
6 TOG , 2 Conference Track
l Dual Octree Graph Networks for Learning Adaptive Volumetric ...
l DiffusionNet: Discretization Agnostic Learning on Surfaces
l Neural Dual Contouring
l Random Walks for Adversarial Meshes
l PCEDNet: A Lightweight Neural Network for Fast and Interactive ...
l Self-Sampling for Neural Point Cloud Consolidation
l ImLoveNet: Misalignment Image-supported Registration Network ...
l DSG-Net: Learning Disentangled Structure and Geometry ...
: Neural Geometry Processing
: , .
, (=
) .