Abstract
Rendering high-resolution (HR) graphics brings substantial computational costs. Efficient graphics super-resolution (SR) methods may achieve HR rendering with small computing resources and have attracted extensive research interests in industry and research communities. We present a new method for real-time SR for computer graphics, namely Super-Resolution by Predicting Offsets (SRPO). Our algorithm divides the image into two parts for processing, i.e., sharp edges and flatter areas. For edges, different from the previous SR methods that take the anti-aliased images as inputs, our proposed SRPO takes advantage of the characteristics of rasterized images to conduct SR on the rasterized images. To complement the residual between HR and low-resolution (LR) rasterized images, we train an ultra-efficient network to predict the offset maps to move the appropriate surrounding pixels to the new positions. For flat areas, we found simple interpolation methods can already generate reasonable output. We finally use a guided fusion operation to integrate the sharp edges generated by the network and flat areas by the interpolation method to get the final SR image. The proposed network only contains 8,434 parameters and can be accelerated by network quantization. Extensive experiments show that the proposed SRPO can achieve superior visual effects at a smaller computational cost than the existing state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For FSRCNN, we use the hyper-parameter of \(D=56\), \(S=12\) and \(M=4\).
- 2.
For ESPCN, we use the hyper-parameter of \(D=22\) and \(S=32\).
- 3.
For eSR family, we select four versions of eSR: eSR-MAX with \(K=3\) and \(C=1\); eSR-TR with \(K=5\) and \(C=2\); eSR-TM with \(K=7\) and \(C=4\); eSR-CNN with \(C=4\), \(D=3\) and \(S=6\).
References
Ahn, N., Kang, B., Sohn, K.A.: Fast, accurate, and lightweight super-resolution with cascading residual network. In: ECCV, pp. 252–268 (2018)
Akenine-Moller, T., Haines, E., Hoffman, N.: Real-Time Rendering. AK Peters/CRC Press (2019)
Chen, H., Gu, J., Zhang, Z.: Attention in attention network for image super-resolution. arXiv preprint arXiv:2104.09497 (2021)
Dai, T., Cai, J., Zhang, Y., Xia, S.T., Zhang, L.: Second-order attention network for single image super-resolution. In: CVPR, pp. 11065–11074 (2019)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. TPAMI 38(2), 295–307 (2015)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323. JMLR Workshop and Conference Proceedings (2011)
Jinjin, G., Haoming, C., Haoyu, C., Xiaoxing, Y., Ren, J.S., Chao, D.: PIPAL: a large-scale image quality assessment dataset for perceptual image restoration. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 633–651. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_37
Gu, J., et al.: NTIRE 2022 challenge on perceptual image quality assessment. In: CVPR Workshops, pp. 951–967 (2022)
Gu, J., Shen, Y., Zhou, B.: Image processing using multi-code GAN prior. In: CVPR, pp. 3012–3021 (2020)
Hui, Z., Gao, X., Yang, Y., Wang, X.: Lightweight image super-resolution with information multi-distillation network. In: ACM MM, pp. 2024–2032 (2019)
Jimenez, J., Echevarria, J.I., Sousa, T., Gutierrez, D.: SMAA: enhanced subpixel morphological antialiasing. In: Computer Graphics Forum, vol. 31, pp. 355–364. Wiley Online Library (2012)
Kaplanyan, A.S., Sochenov, A., Leimkühler, T., Okunev, M., Goodall, T., Rufo, G.: DeepFovea: neural reconstruction for foveated rendering and video compression using learned statistics of natural videos. TOG 38(6), 1–13 (2019)
Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: CVPR, pp. 1646–1654 (2016)
Kim, J., Kwon Lee, J., Mu Lee, K.: Deeply-recursive convolutional network for image super-resolution. In: CVPR, pp. 1637–1645 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 4681–4690 (2017)
Li, Z., et al.: Blueprint separable residual network for efficient image super-resolution. In: CVPR, pp. 833–843 (2022)
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPR Workshops, pp. 136–144 (2017)
Michelini, P.N., Lu, Y., Jiang, X.: edge-SR: super-resolution for the masses. In: WACV, pp. 1078–1087 (2022)
Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS, vol. 32, pp. 8026–8037 (2019)
Reshetov, A.: Morphological antialiasing. In: Proceedings of the Conference on High Performance Graphics, pp. 109–116 (2009)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR, pp. 1874–1883 (2016)
Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: CVPR, pp. 3147–3155 (2017)
Thomas, M.M., Vaidyanathan, K., Liktor, G., Forbes, A.G.: A reduced-precision network for image reconstruction. TOG 39(6), 1–12 (2020)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 63–79. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_5
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600–612 (2004)
Xiao, L., Nouri, S., Chapman, M., Fix, A., Lanman, D., Kaplanyan, A.: Neural supersampling for real-time rendering. TOG 39(4), 142-1 (2020)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR, pp. 586–595 (2018)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 286–301 (2018)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47–57 (2016)
Zhao, H., Kong, X., He, J., Qiao, Yu., Dong, C.: Efficient image super-resolution using pixel attention. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12537, pp. 56–72. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-67070-2_3
Acknowledgement
This work was partly supported by SZSTC Grant No. JCYJ20190809172201639 and WDZC20200820200655001, Shenzhen Key Laboratory ZDSYS20210623092001004. We sincerely thank Yongfei Pu, Yuanlong Li, Jieming Li and Yuanlin Chen for contributing to this study.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gu, J. et al. (2022). Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13679. Springer, Cham. https://doi.org/10.1007/978-3-031-19800-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-19800-7_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19799-4
Online ISBN: 978-3-031-19800-7
eBook Packages: Computer ScienceComputer Science (R0)