
T3DNet proposes a two-stage method for compressing 3D point cloud models, achieving high compression rates without significant accuracy sacrifice.


coremsg

t3dnet-compressing-point-cloud-models-for-lightweight-3d-recognition


T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition



提案されたT3DNet（Tiny 3D Network with augmEntation and disTillation）メソッドは、高い圧縮率を実現しながら、元のモデルと比較してわずかな精度低下で高性能を達成します。
