251 citations · 424 across the 20 of their papers we have counts for
20 papers
Interaction-Driven Active 3D Reconstruction with Object Interiors
Zihao Yan, Fubao Su, Mingyang Wang +3
We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i.e., unexp…
Neural Packing: from Visual Sensing to Reinforcement Learning
Juzhan Xu, Minglun Gong, Hao Zhang +2
We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via…
Semi-Weakly Supervised Object Kinematic Motion Prediction
Gengxin Liu, Qian Sun, Haibin Huang +5
Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological str…
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Xueyi Liu, Ji Zhang, Ruizhen Hu +3
Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce t…
ARO-Net: Learning Implicit Fields from Anchored Radial Observations
Yizhi Wang, Zeyu Huang, Ariel Shamir +3
We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes that is category-agnostic and generalizable amid sig…
Asynchronous Collaborative Autoscanning with Mode Switching for Multi-Robot Scene Reconstruction
Junfu Guo, Changhao Li, Xi Xia +2
When conducting autonomous scanning for the online reconstruction of unknown indoor environments, robots have to be competent at exploring scene structure and reconstructing object…
Shape Completion with Points in the Shadow
Bowen Zhang, Xi Zhao, He Wang +1
Single-view point cloud completion aims to recover the full geometry of an object based on only limited observation, which is extremely hard due to the data sparsity and occlusion.…
NIFT: Neural Interaction Field and Template for Object Manipulation
Zeyu Huang, Juzhan Xu, Sisi Dai +4
We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few…
Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation
Gengxin Liu, Oliver van Kaick, Hui Huang +1
Since the preparation of labeled data for training semantic segmentation networks of point clouds is a time-consuming process, weakly supervised approaches have been introduced to…
Photo-to-Shape Material Transfer for Diverse Structures
Ruizhen Hu, Xiangyu Su, Xiangkai Chen +2
We introduce a method for assigning photorealistic relightable materials to 3D shapes in an automatic manner. Our method takes as input a photo exemplar of a real object and a 3D o…
Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction
Qijin She, Ruizhen Hu, Juzhan Xu +3
We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue i…
Point cloud completion via structured feature maps using a feedback network
Zejia Su, Haibin Huang, Chongyang Ma +2
In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structure…
Consistent Two-Flow Network for Tele-Registration of Point Clouds
Zihao Yan, Zimu Yi, Ruizhen Hu +3
Rigid registration of partial observations is a fundamental problem in various applied fields. In computer graphics, special attention has been given to the registration between tw…
Shape-driven Coordinate Ordering for Star Glyph Sets via Reinforcement Learning
Ruizhen Hu, Bin Chen, Juzhan Xu +3
We present a neural optimization model trained with reinforcement learning to solve the coordinate ordering problem for sets of star glyphs. Given a set of star glyphs associated t…
TAP-Net: Transport-and-Pack using Reinforcement Learning
Ruizhen Hu, Juzhan Xu, Bin Chen +3
We introduce the transport-and-pack(TAP) problem, a frequently encountered instance of real-world packing, and develop a neural optimization solution based on reinforcement learnin…
Predictive and Generative Neural Networks for Object Functionality
Ruizhen Hu, Zihao Yan, Jingwen Zhang +4
Humans can predict the functionality of an object even without any surroundings, since their knowledge and experience would allow them to "hallucinate" the interaction or usage sce…
RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud
Zihao Yan, Ruizhen Hu, Xingguang Yan +4
We introduce RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D…
FAME: 3D Shape Generation via Functionality-Aware Model Evolution
Yanran Guan, Han Liu, Kun Liu +8
We introduce a modeling tool which can evolve a set of 3D objects in a functionality-aware manner. Our goal is for the evolution to generate large and diverse sets of plausible 3D…
Graph2Plan: Learning Floorplan Generation from Layout Graphs
Ruizhen Hu, Zeyu Huang, Yuhan Tang +3
We introduce a learning framework for automated floorplan generation which combines generative modeling using deep neural networks and user-in-the-loop designs to enable human user…
Hatching for 3D prints: line-based halftoning for dual extrusion fused deposition modeling
Tim Kuipers, Willemijn Elkhuizen, Jouke Verlinden +1
This work presents a halftoning technique to manufacture 3D objects with the appearance of continuous grayscale imagery for Fused Deposition Modeling (FDM) printers. While droplet-…