• Publications
  • Influence
Enhanced Pix2pix Dehazing Network
In this paper, we reduce the image dehazing problem to an image-to-image translation problem, and propose Enhanced Pix2pix Dehazing Network (EPDN), which generates a haze-free image without relying on the physical scattering model. Expand
  • 78
  • 21
  • PDF
Microwave-assisted extraction of silkworm pupal oil and evaluation of its fatty acid composition, physicochemical properties and antioxidant activities.
  • Bin Hu, Cheng Li, +4 authors Yizi Chen
  • Chemistry, Medicine
  • Food chemistry
  • 15 September 2017
Microwave-assisted extraction (MAE) of oil from silkworm pupae was firstly performed in the present research. The response surface methodology was applied to optimize the parameters for MAE. TheExpand
  • 27
  • 2
NTIRE 2019 Image Dehazing Challenge Report
This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. Expand
  • 5
  • PDF
Multi-Scale Adaptive Dehazing Network
We introduce an adaptive distillation network to solve the dehaze problem with non-uniform haze, which does not rely on the physical scattering model. Expand
  • 6
  • PDF
Influence of DBD-grafted multi-carboxyl polyurethane on interfacial properties of PBO fibre-reinforced BMI resin composites
Abstract The poor adhesion between polybenzoxazole (PBO) fibre and resin can lead to limitations in the composites formed for practical applications. Air atmospheric dielectric barrier discharge wasExpand
  • 2
Improvement of the interfacial properties of PBO/Epoxy composites by online continuous plasma grafting with polyurethane
Abstract Grafting modification is an effective means to improve the interfacial bonding properties of fibre composites. In this study, a series of grafted poly(p-phenyleneExpand
Systematic Approaches To Music Rehearsal Segmentation
Practice is always the secret to the success of musicians. Many musicians record their rehearsal sessions and listen back to reflect on their practice. However, the rehearsal sessions areExpand
Combining Deep Learning and Mathematical Morphology for Historical Map Segmentation
The digitization of historical maps enables the study of ancient, fragile, unique, and hardly accessible information sources. Expand