activity
20182022
most citedProgPrompt: Generating Situated Robot Task Plans using Large Language Models

44 citations · 79 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2022

Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation

Yunzhi Lin, Jonathan Tremblay, Stephen Tyree +2

We propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category. Our method takes as i…

cs.CV20219 cited

NViSII: A Scriptable Tool for Photorealistic Image Generation

Nathan Morrical, Jonathan Tremblay, Yunzhi Lin +4

We present a Python-based renderer built on NVIDIA's OptiX ray tracing engine and the OptiX AI denoiser, designed to generate high-quality synthetic images for research in computer…

cs.CV20217 cited

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

Yu-Wei Chao, Wei Yang, Yu Xiang +9

We introduce DexYCB, a new dataset for capturing hand grasping of objects. We first compare DexYCB with a related one through cross-dataset evaluation. We then present a thorough b…

cs.CV2020

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

Zheng Tang, Milind Naphade, Stan Birchfield +5

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging d…

cs.CV2019

Few-Shot Viewpoint Estimation

Hung-Yu Tseng, Shalini De Mello, Jonathan Tremblay +4

Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still v…

cs.CV2018

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

Jonathan Tremblay, Aayush Prakash, David Acuna +7

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the techniqu…