67 citations · 164 across the 12 of their papers we have counts for
12 papers
ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
Jiayuan Gu, Fanbo Xiang, Xuanlin Li +12
Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI. However, existing benchmarks,…
Multi-skill Mobile Manipulation for Object Rearrangement
Jiayuan Gu, Devendra Singh Chaplot, Hao Su +1
We study a modular approach to tackle long-horizon mobile manipulation tasks for object rearrangement, which decomposes a full task into a sequence of subtasks. To tackle the entir…
Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation
Xiaoshuai Zhang, Rui Chen, Ang Li +11
In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of…
Deep Feedback Inverse Problem Solver
Wei-Chiu Ma, Shenlong Wang, Jiayuan Gu +3
We present an efficient, effective, and generic approach towards solving inverse problems. The key idea is to leverage the feedback signal provided by the forward process and learn…
Compositionally Generalizable 3D Structure Prediction
Songfang Han, Jiayuan Gu, Kaichun Mo +4
Single-image 3D shape reconstruction is an important and long-standing problem in computer vision. A plethora of existing works is constantly pushing the state-of-the-art performan…
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Tongzhou Mu, Jiayuan Gu, Zhiwei Jia +2
We study how to learn a policy with compositional generalizability. We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student p…
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Hao Tang, Zhiao Huang, Jiayuan Gu +2
Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems. Tak…
Weakly-supervised 3D Shape Completion in the Wild
Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam +5
3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned. Different from pr…
Multi-view PointNet for 3D Scene Understanding
Maximilian Jaritz, Jiayuan Gu, Hao Su
Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data li…
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
Liwei Wang, Lunjia Hu, Jiayuan Gu +4
It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory an…
Learning Region Features for Object Detection
Jiayuan Gu, Han Hu, Liwei Wang +2
While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods. This work p…
Relation Networks for Object Detection
Han Hu, Jiayuan Gu, Zheng Zhang +2
Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learn…