Show simple item record

dc.contributor.authorPang, Youxin
dc.contributor.authorYuan, Mengke
dc.contributor.authorFu, Qiang
dc.contributor.authorYan, Dong Ming
dc.date.accessioned2020-10-14T11:49:24Z
dc.date.available2020-10-14T11:49:24Z
dc.date.issued2020-08-17
dc.identifier.citationPang, Y., Yuan, M., Fu, Q., & Yan, D.-M. (2020). Reflection Removal via Realistic Training Data Generation. ACM SIGGRAPH 2020 Posters. doi:10.1145/3388770.3407419
dc.identifier.isbn9781450379731
dc.identifier.doi10.1145/3388770.3407419
dc.identifier.urihttp://hdl.handle.net/10754/665577
dc.description.abstractWe present a valid polarization-based reflection contaminated image synthesis method, which can provide adequate, diverse and authentic training dataset. Meanwhile, we enhance the neural network by introducing the reflection information as guidance and utilizing adaptive convolution kernel size to fuse multi-scale information. We demonstrate that the proposed approach achieves convincing improvements over state of the arts.
dc.description.sponsorshipThis work was supported by the National Key R&D Program of China (2019YFB2204104 and 2018YFB2100602). (Portions of) the research in this paper used the 'SIR2' Dataset made available by the ROSE Lab at the Nanyang Technological University, Singapore.
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.urlhttps://dl.acm.org/doi/10.1145/3388770.3407419
dc.rightsArchived with thanks to ACM
dc.titleReflection Removal via Realistic Training Data Generation
dc.typeConference Paper
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.date2020-08-17
dc.conference.nameACM SIGGRAPH 2020 Posters - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2020
dc.conference.locationVirtual, Online, USA
dc.eprint.versionPost-print
dc.contributor.institutionNLPR-CASIA School of AI, UCAS
kaust.personFu, Qiang
dc.identifier.eid2-s2.0-85091969870
refterms.dateFOA2020-10-27T06:34:58Z
dc.date.published-online2020-08-17
dc.date.published-print2020-08-17


Files in this item

Thumbnail
Name:
Reflection Removal via Realistic Training Data Generation.pdf
Size:
1.508Mb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record