Name
Abstract | ||
|---|---|---|
We present a new, publicly-available image dataset generated by the NVIDIA Deep Learning Data Synthesizer intended for use in object detection, pose estimation, and tracking applications. This dataset contains 144k stereo image pairs that synthetically combine 18 camera viewpoints of three photorealistic virtual environments with up to 10 objects (chosen randomly from the 21 object models of the YCB dataset ) and flying distractors. Object and camera pose, scene lighting, and quantity of objects and distractors were randomized. Each provided view includes RGB, depth, segmentation, and surface normal images, all pixel level. We describe our approach for domain randomization and provide insight into the decisions that produced the dataset. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPRW.2019.00063 | 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
Keywords | Field | DocType |
object models,domain randomization,surface normal images,object camera,distractors,YCB dataset,photorealistic virtual environments,camera viewpoints,stereo image pairs,tracking applications,object detection,NVIDIA Deep Learning Data Synthesizer,publicly-available image dataset,3d object pose recognition,synthetic image dataset,SIDOD | Computer vision,Pattern recognition,Computer science,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
2160-7508 | 978-1-7281-2507-7 | 3 |
PageRank | References | Authors |
0.44 | 2 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mona Jalal | 1 | 8 | 1.58 |
| Josef Spjut | 2 | 101 | 10.20 |
| Ben Boudaoud | 3 | 16 | 3.48 |
| M. Betke | 4 | 89 | 19.94 |