“Towards Large-Scale Super Resolution Datasets via Learned Downsampling of Ray-Traced Renderings” by Vavilala and Meyer
Conference:
Type(s):
Entry Number: 05
Title:
- Towards Large-Scale Super Resolution Datasets via Learned Downsampling of Ray-Traced Renderings
Presenter(s)/Author(s):
Abstract:
Delivering high resolution content is a challenge in the film and games industries due to the cost of photorealistic ray-traced rendering. Image upscaling techniques are commonly used to obtain a high-resolution result from a low-resolution render. Recently, deep learned upscaling has started to make an impact in production settings, synthesizing sharper and more detailed imagery than previous methods. The quality of a super resolution model depends on the size of its dataset, which can be expensive to generate at scale due to the large number of ray-traced pairs of renders required. In this report, we discuss our experiments training an additional neural network to learn the degradation operator, which can be used to rapidly generate low resolution images from existing high-resolution renders. Our testing on production scenes shows that super resolution networks trained with a large synthetic dataset produce fewer artifacts and better reconstruction quality than net- works trained on a smaller rendered dataset alone, and compare favorably to recent state of the art blind synthetic data techniques.
References:
Victor Cornillere, Abdelaziz Djelouah, Wang Yifan, Olga Sorkine-Hornung, and Christo-
pher Schroers. 2019. Blind image super-resolution with spatially variant degrada-
tions. ACM Transactions on Graphics (TOG) 38, 6 (2019), 1–13.
Vaibhav Vavilala and Mark Meyer. 2020. Deep Learned Super Resolution for Feature
Film Production. In ACM SIGGRAPH 2020 Talks (SIGGRAPH ’20). Association for
Computing Machinery, New York, NY, USA, Article 41, 2 pages. https://doi.org/10.
1145/3388767.3407334
Yifan Wang, Federico Perazzi, Brian McWilliams, Alexander Sorkine-Hornung, Olga
Sorkine-Hornung, and Christopher Schroers. 2018. A fully progressive approach to
single-image super-resolution. In Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition Workshops. 864–873.
Acknowledgements:
The authors thank Christopher Schroers, Aziz Djelouah, and Jeremy Newlin for helpful suggestions and support.
