Upgrade to Pro — share decks privately, control downloads, hide ads and more …

SIGGRAPH 2022: Neural Geometry Processing

SIGGRAPH 2022: Neural Geometry Processing

SIGGRAPH 2022勉強会で使ったスライドです。
https://siggraph.xyz/s2022/

Tatsuya Yatagawa

August 27, 2022
Tweet

More Decks by Tatsuya Yatagawa

Other Decks in Technology

Transcript

  1. 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)
  2. Marching Cubes ( : Dual Contouring, : Marching Cubes) Dual

    Contouring Dual Contouring , Marching Cubes
  3. l MC (MC ) l MC , , : Neural

    Marching Cubes l , (= ) l
  4. l NMC , DC l NMC , DC l NDC

    , UNDC l DC l UNDC , Neural Dual Contouring
  5. (Scale-Space Matrix) l Growing Least Squares [Mellado+ 2012] l ,

    - , , , . l 6 , 16 (=SSM) . PCEDNet (Point Cloud Edge Detection Network) l SSM (= 6 16 ) .
  6. l , , , l MLP, CNN l CNN ,

    , l SSM 4-128 , l , 16 4 16 128
  7. : l positive ( ) negative ( ) . l

    , (source) (target) , positive l
  8. l 2 + ( ) ( ) l as-consistent-as- possible

    (9 BBox ) [Guo+ 2019] l one-hot MLP l ACAP BBox , .
  9. 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 : , . , (= ) .