May 7, 2024, 4:47 a.m. | Jinmin Li, Tao Dai, Jingyun Zhang, Kang Liu, Jun Wang, Shaoming Wang, Shu-Tao Xia, rizen guo

cs.CV updates on arXiv.org arxiv.org

arXiv:2405.02941v1 Announce Type: new
Abstract: Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details, which thus hinders their real applications. To address this issue, we propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results. Unlike previous methods that model high-frequency information as standard Gaussian distribution directly, …

arxiv cs.cv flow networks type

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