93 citations · 706 across the 49 of their papers we have counts for
20 papers · 1 filter
Learning Continuous Environment Fields via Implicit Functions
Xueting Li, Shalini De Mello, Xiaolong Wang +3
We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory. We demonstrate that…
Multi-Person 3D Motion Prediction with Multi-Range Transformers
Jiashun Wang, Huazhe Xu, Medhini Narasimhan +1
We propose a novel framework for multi-person 3D motion trajectory prediction. Our key observation is that a human's action and behaviors may highly depend on the other persons aro…
Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
Jianglong Ye, Yuntao Chen, Naiyan Wang +1
Tracking and reconstructing 3D objects from cluttered scenes are the key components for computer vision, robotics and autonomous driving systems. While recent progress in implicit…
Video Autoencoder: self-supervised disentanglement of static 3D structure and motion
Zihang Lai, Sifei Liu, Alexei A. Efros +1
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity…
Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization
Chieko Sarah Imai, Minghao Zhang, Yuchen Zhang +4
Developing robust vision-guided controllers for quadrupedal robots in complex environments, with various obstacles, dynamical surroundings and uneven terrains, is very challenging.…
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Yuzhe Qin, Yueh-Hua Wu, Shaowei Liu +4
While significant progress has been made on understanding hand-object interactions in computer vision, it is still very challenging for robots to perform complex dexterous manipula…
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Ruihan Yang, Minghao Zhang, Nicklas Hansen +2
We propose to address quadrupedal locomotion tasks using Reinforcement Learning (RL) with a Transformer-based model that learns to combine proprioceptive information and high-dimen…
Test-Time Personalization with a Transformer for Human Pose Estimation
Yizhuo Li, Miao Hao, Zonglin Di +2
We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose…
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
Nicklas Hansen, Hao Su, Xiaolong Wang
While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments re…
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
Shaowei Liu, Hanwen Jiang, Jiarui Xu +2
Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations ar…
Single RGB-D Camera Teleoperation for General Robotic Manipulation
Quan Vuong, Yuzhe Qin, Runlin Guo +3
We propose a teleoperation system that uses a single RGB-D camera as the human motion capture device. Our system can perform general manipulation tasks such as cloth folding, hamme…
DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation
Minghao Zhang, Pingcheng Jian, Yi Wu +2
We address the problem of safely solving complex bimanual robot manipulation tasks with sparse rewards. Such challenging tasks can be decomposed into sub-tasks that are accomplisha…
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
Haiping Wu, Xiaolong Wang
Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two differ…
A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation
Jiteng Mu, Weichao Qiu, Adam Kortylewski +3
Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been d…
Hand-Object Contact Consistency Reasoning for Human Grasps Generation
Hanwen Jiang, Shaowei Liu, Jiashun Wang +1
While predicting robot grasps with parallel jaw grippers have been well studied and widely applied in robot manipulation tasks, the study on natural human grasp generation with a m…
Robust Object Detection via Instance-Level Temporal Cycle Confusion
Xin Wang, Thomas E. Huang, Benlin Liu +4
Building reliable object detectors that are robust to domain shifts, such as various changes in context, viewpoint, and object appearances, is critical for real-world applications.…
Solving Compositional Reinforcement Learning Problems via Task Reduction
Yunfei Li, Yilin Wu, Huazhe Xu +2
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction…
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
Zhenggang Tang, Chao Yu, Boyuan Chen +6
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization a…
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective
Jiarui Xu, Xiaolong Wang
Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixe…
Region Similarity Representation Learning
Tete Xiao, Colorado J Reed, Xiaolong Wang +2
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and se…