74 citations · 229 across the 8 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.CV2019★ 47 cited
Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules
Xin Wen, Zhizhong Han, Xinhai Liu +1
Learning discriminative shape representation directly on point clouds is still challenging in 3D shape analysis and understanding. Recent studies usually involve three steps: first…
cs.CV2019★ 74 cited
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
Xinhai Liu, Zhizhong Han, Xin Wen +2
Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learni…
cs.CV2019★ 7 cited
Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
Zhizhong Han, Xinhai Liu, Yu-Shen Liu +1
Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute lo…