Name:
Reflection Removal via Realistic Training Data Generation.pdf
Size:
1.508Mb
Format:
PDF
Description:
Accepted manuscript
Type
Conference PaperKAUST Department
Visual Computing Center (VCC)Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Date
2020-08-17Online Publication Date
2020-08-17Print Publication Date
2020-08-17Permanent link to this record
http://hdl.handle.net/10754/665577
Metadata
Show full item recordAbstract
We 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.Citation
Pang, Y., Yuan, M., Fu, Q., & Yan, D.-M. (2020). Reflection Removal via Realistic Training Data Generation. ACM SIGGRAPH 2020 Posters. doi:10.1145/3388770.3407419Sponsors
This 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.Conference/Event name
ACM SIGGRAPH 2020 Posters - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2020ISBN
9781450379731Additional Links
https://dl.acm.org/doi/10.1145/3388770.3407419ae974a485f413a2113503eed53cd6c53
10.1145/3388770.3407419