UnrealCV: Virtual Worlds for Computer Vision

By Weichao Qiu, Fangwei Zhong, Yi Zhang, Siyuan Qiao, Zihao Xiao, Tae Soo Kim, Yizhou Wang. 2017

251 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects (2018, methodology): “Previous research has successfully used 3D graphics as a diagnostic tool for computer vision systems [7, 31, 47, 32, 50].”
SAPIEN: A SimulAted Part-Based Interactive ENvironment (2020, background): “To allow for more interactive features in environments, researchers leverage partial functionalities of game engines or physics engine to provide photorealistic rendering together with interactions [54, 34, 25, 38, 3, 59, 13, 26].”
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications (2017, background): “2017) or UnrealCV (Qiu et al. 2017) with Sim4CV, and make contributions to our simulator project.”
ESIM: an Open Event Camera Simulator (2018, background): “To meet this demand, an unprecendented number of simulators (CARLA [6], Microsoft Airsim [7], UnrealCV [8]) has been proposed for standard cameras.”
An Efficient Sampling-Based Method for Online Informative Path Planning in Unknown Environments (2019, methodology): “The perception interface2 is based on the UnrealCV computer vision plugin [26] and is”
Depth Anything V2 (2024, unknown): “Moreover, we can quickly enlarge synthetic training images by collecting from graphics engines [58, 63, 53], which would not cause any privacy or ethical concerns, as compared to real images.”
The RobotriX: An Extremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions (2018, unknown): “For that, We leveraged UnrealCV [30].”
QuadricSLAM: Dual Quadrics From Object Detections as Landmarks in Object-Oriented SLAM (2018, methodology): “With this in mind, we created a synthetic dataset using the UnrealCV plugin [33], containing ground truth camera trajectory xi ∈ SE(3), 2-D object bounding boxes bij , and 3-D object bounding boxes.”
Scene Text Detection and Recognition: The Deep Learning Era (2018, unknown): “UnrealCV (Qiu et al., 2017) to synthesize scene text images.”
Deep Learning-based Human Pose Estimation: A Survey (2020, methodology): “UnrealCV [268] was used to render multi-view images and depth maps from 3D models.”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “Some of the platforms are built towards this effort [12, 45, 76, 103, 107].”
Synthetic Data for Deep Learning (2019, methodology): “[466, 467], an open-source plugin for the popular game engine Unreal Engine 4 that provides commands that allow to get and set camera location and field of view, get the set of objects in a scene together with their positions, set lighting parameters, modify properties of the objects such as materia”