WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion

Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel framework for automatically generating a large, realistic d...

Full description

Bibliographic Details

Published in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 9514 - 9524
Main Authors:	Vuong, Khiem, Reddy, N Dinesh, Tamburo, Robert, Narasimhan, Srinivasa G.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 16.06.2024
Subjects:	3D from single images computer vision Image segmentation Reconstruction algorithms Shape Three-dimensional displays Training Training data Urban areas
ISSN:	1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!