all AI news
WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion
March 29, 2024, 4:44 a.m. | Khiem Vuong, N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan
cs.CV updates on arXiv.org arxiv.org
Abstract: 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 dataset of dynamic objects under occlusions using freely available time-lapse imagery. By leveraging off-the-shelf 2D (bounding box, segmentation, keypoint) and 3D (pose, shape) predictions as pseudo-groundtruth, unoccluded 3D objects are identified automatically …
3d object abstract annotations arxiv cs.cv current data dynamic environments framework ground-truth novel object objects scale struggle training training data truth type understanding urban work
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US