Files in this item



application/pdfFA20-ECE499-Thesis-Wang, Jiahong.pdf (9MB)Restricted to U of Illinois
(no description provided)PDF


Title:GTAMesh Dataset: Semantic 3D Perception Dataset
Author(s):Wang, Jiahong
Contributor(s):Schwing, Alexander
Subject(s):3D dataset
synthetic dataset
3D vision
single-view reconstruction
Abstract:Abundance in 2D segmentation datasets has enabled the training of accurate 2D perception models. However, collecting real-world 3D perception datasets is challenging and time-consuming, and therefore, 3D perception datasets are few and often contain limited categories of objects. In this project, we aim to collect a large-scale synthetic dataset, the GTAMesh dataset, containing annotations for 3D geometry of objects represented as meshes. To this end, we use the game engine GTA-V for collecting the data. The mesh information of variegated objects can be extracted by hooking into the rendering pipeline. We show some application cases and develop a temporal baseline model for 3D reconstruction to demonstrate the effectiveness of our dataset.
Issue Date:2020-12
Sponsor:National Science Foundation's Major Research Instrumentation program, grant #1725729
Date Available in IDEALS:2021-01-04

This item appears in the following Collection(s)

Item Statistics