Stan Birchfield

Deep Two-View Structure-from-Motion Revisited

Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruc...
04/01/2021 ∙ by Jianyuan Wang, et al. ∙ 0 ∙ share

read it
Multi-view Fusion for Multi-level Robotic Scene Understanding

We present a system for multi-level scene awareness for robotic manipula...
03/25/2021 ∙ by Yunzhi Lin, et al. ∙ 0 ∙ share

read it
Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs

We present a visually grounded hierarchical planning algorithm for long-...
12/14/2020 ∙ by Yifeng Zhu, et al. ∙ 0 ∙ share

read it
Displacement-Invariant Cost Computation for Efficient Stereo Matching

Although deep learning-based methods have dominated stereo matching lead...
12/01/2020 ∙ by Yiran Zhong, et al. ∙ 9 ∙ share

read it
Fast Uncertainty Quantification for Deep Object Pose Estimation

Deep learning-based object pose estimators are often unreliable and over...
11/16/2020 ∙ by Guanya Shi, et al. ∙ 0 ∙ share

read it
Joint Space Control via Deep Reinforcement Learning

The dominant way to control a robot manipulator uses hand-crafted differ...
11/12/2020 ∙ by Visak Kumar, et al. ∙ 0 ∙ share

read it
Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera

We present a robotic grasping system that uses a single external monocul...
08/26/2020 ∙ by Jonathan Tremblay, et al. ∙ 0 ∙ share

read it
Improving Deep Stereo Network Generalization with Geometric Priors

End-to-end deep learning methods have advanced stereo vision in recent y...
08/25/2020 ∙ by Jialiang Wang, et al. ∙ 8 ∙ share

read it
RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies

Generating robot motion for multiple tasks in dynamic environments is ch...
07/25/2020 ∙ by Ching-An Cheng, et al. ∙ 0 ∙ share

read it
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views

Autonomous driving requires the inference of actionable information such...
06/09/2020 ∙ by Ke Chen, et al. ∙ 0 ∙ share

read it
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

In comparison with person re-identification (ReID), which has been widel...
05/02/2020 ∙ by Zheng Tang, et al. ∙ 1 ∙ share

read it
Contextual Reinforcement Learning of Visuo-tactile Multi-fingered Grasping Policies

Using simulation to train robot manipulation policies holds the promise ...
11/21/2019 ∙ by Visak Kumar, et al. ∙ 0 ∙ share

read it
Camera-to-Robot Pose Estimation from a Single Image

We present an approach for estimating the pose of a camera with respect ...
11/21/2019 ∙ by Timothy E. Lee, et al. ∙ 0 ∙ share

read it
DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

Teleoperation offers the possibility of imparting robotic systems with s...
10/07/2019 ∙ by Ankur Handa, et al. ∙ 20 ∙ share

read it
Directional Semantic Grasping of Real-World Objects: From Simulation to Reality

We present a deep reinforcement learning approach to grasp semantically ...
09/04/2019 ∙ by Shariq Iqbal, et al. ∙ 0 ∙ share

read it
Few-Shot Viewpoint Estimation

Viewpoint estimation for known categories of objects has been improved s...
05/13/2019 ∙ by Hung-Yu Tseng, et al. ∙ 4 ∙ share

read it
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

Urban traffic optimization using traffic cameras as sensors is driving t...
03/21/2019 ∙ by Zheng Tang, et al. ∙ 8 ∙ share

read it
RMPflow: A Computational Graph for Automatic Motion Policy Generation

We develop a novel policy synthesis algorithm, RMPflow, based on geometr...
11/16/2018 ∙ by Ching-An Cheng, et al. ∙ 0 ∙ share

read it
Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

We present structured domain randomization (SDR), a variant of domain ra...
10/23/2018 ∙ by Aayush Prakash, et al. ∙ 0 ∙ share

read it
Robust Learning of Tactile Force Estimation through Robot Interaction

Current methods for estimating force from tactile sensor signals are eit...
10/15/2018 ∙ by Balakumar Sundaralingam, et al. ∙ 0 ∙ share

read it
Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects

Using synthetic data for training deep neural networks for robotic manip...
09/27/2018 ∙ by Jonathan Tremblay, et al. ∙ 0 ∙ share

read it
Region Growing Curriculum Generation for Reinforcement Learning

Learning a policy capable of moving an agent between any two states in t...
07/04/2018 ∙ by Artem Molchanov, et al. ∙ 0 ∙ share

read it
Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations

We present a system to infer and execute a human-readable program from a...
05/18/2018 ∙ by Jonathan Tremblay, et al. ∙ 0 ∙ share

read it
Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation

We present a new dataset, called Falling Things (FAT), for advancing the...
04/18/2018 ∙ by Jonathan Tremblay, et al. ∙ 0 ∙ share

read it
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization

We present a system for training deep neural networks for object detecti...
04/18/2018 ∙ by Jonathan Tremblay, et al. ∙ 0 ∙ share

read it
On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach

We revisit the problem of visual depth estimation in the context of auto...
03/26/2018 ∙ by Nikolai Smolyanskiy, et al. ∙ 0 ∙ share

read it
Efficient Hierarchical Graph-Based Segmentation of RGBD Videos

We present an efficient and scalable algorithm for segmenting 3D RGBD po...
01/26/2018 ∙ by Steven Hickson, et al. ∙ 0 ∙ share

read it
An Energy Minimization Approach to 3D Non-Rigid Deformable Surface Estimation Using RGBD Data

We propose an algorithm that uses energy mini- mization to estimate the ...
08/02/2017 ∙ by Bryan Willimon, et al. ∙ 0 ∙ share

read it

Stan Birchfield

Featured Co-authors