19 citations · 113 across the 16 of their papers we have counts for
4 papers · 1 filter
Zero-shot point cloud segmentation by transferring geometric primitives
Runnan Chen, Xinge Zhu, Nenglun Chen +4
We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements…
CreatureShop: Interactive 3D Character Modeling and Texturing from a Single Color Drawing
Congyi Zhang, Lei Yang, Nenglun Chen +5
Creating 3D shapes from 2D drawings is an important problem with applications in content creation for computer animation and virtual reality. We introduce a new sketch-based system…
Self-Supervised Image Representation Learning with Geometric Set Consistency
Nenglun Chen, Lei Chu, Hao Pan +2
We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as…
Towards 3D Scene Understanding by Referring Synthetic Models
Runnan Chen, Xinge Zhu, Nenglun Chen +5
Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In…