all AI news
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects. (arXiv:2208.03792v2 [cs.CV] UPDATED)
Nov. 24, 2022, 7:17 a.m. | Qiyu Dai, Jiyao Zhang, Qiwei Li, Tianhao Wu, Hao Dong, Ziyuan Liu, Ping Tan, He Wang
cs.CV updates on arXiv.org arxiv.org
Commercial depth sensors usually generate noisy and missing depths,
especially on specular and transparent objects, which poses critical issues to
downstream depth or point cloud-based tasks. To mitigate this problem, we
propose a powerful RGBD fusion network, SwinDRNet, for depth restoration. We
further propose Domain Randomization-Enhanced Depth Simulation (DREDS) approach
to simulate an active stereo depth system using physically based rendering and
generate a large-scale synthetic dataset that contains 130K photorealistic RGB
images along with their simulated depths carrying realistic …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US