Generative Adversarial Shaders for Real-Time Realism Enhancement

被引:0
|
作者
Salmi, A. [1 ]
Csefalvay, Sz [1 ]
Imber, J. [1 ]
机构
[1] Imaginat Technol, Kings Langley, England
关键词
Computing methodologies ? Computer graphics; Machine learning; Image processing; Rendering; Graphics processors;
D O I
10.1111/cgf.14870
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Application of realism enhancement methods, particularly in real-time and resource-constrained settings, has been frustrated by the expense of existing methods. These achieve high quality results only at the cost of long runtimes and high bandwidth, memory, and power requirements. We present an efficient alternative: a high-performance, generative shader-based approach that adapts machine learning techniques to real-time applications, even in resource-constrained settings such as embedded and mobile GPUs. The proposed learnable shader pipeline comprises differentiable functions that can be trained in an end-to-end manner using an adversarial objective, allowing for faithful reproduction of the appearance of a target image set without manual tuning. The shader pipeline is optimized for highly efficient execution on the target device, providing temporally stable, faster-than-real time results with quality competitive with many neural network-based methods.
引用
收藏
页数:12
相关论文
共 50 条
  • [21] Real-Time Detection Algorithm for Kiwifruit Canker Based on a Lightweight and Efficient Generative Adversarial Network
    Xiang, Ying
    Yao, Jia
    Yang, Yiyu
    Yao, Kaikai
    Wu, Cuiping
    Yue, Xiaobin
    Li, Zhenghao
    Ma, Miaomiao
    Zhang, Jie
    Gong, Guoshu
    PLANTS-BASEL, 2023, 12 (17):
  • [22] AUTOMATED REAL-TIME PHARMACOKINETIC (PK) PREDICTION WITH GENERATIVE ADVERSARIAL NETWORK (GAN) METHODOLOGY.
    Hsieh, H.
    Liu, G.
    Lu, D.
    Liu, K.
    Lu, J.
    CLINICAL PHARMACOLOGY & THERAPEUTICS, 2021, 109 : S13 - S13
  • [23] Real-time Semantic Segmentation of Sheep Skeleton Image Based on Generative Adversarial Network and ICNet
    Zhao S.
    Wang S.
    Bai Y.
    Hao G.
    Tu B.
    Wang, Shucai (wsc01@mail.hzau.edu.cn), 1600, Chinese Society of Agricultural Machinery (52): : 329 - 339and380
  • [24] Generative adversarial networks for SAR image realism
    Lewis, Benjamin
    Liu, Jennifer
    Wong, Amy
    ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXV, 2018, 10647
  • [25] A Perceptual Evaluation of Generative Adversarial Network Real-time Synthesized Drum Sounds in a Virtual Environment
    Chang, Minwook
    Kim, Youngwon Ryan
    Kim, Gerard Jounghyun
    2018 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND VIRTUAL REALITY (AIVR), 2018, : 144 - 148
  • [26] PLCNet: Real-time Packet Loss Concealment with Semi-supervised Generative Adversarial Network
    Liu, Baiyun
    Song, Qi
    Yang, Mingxue
    Yuan, Wuwen
    Wang, Tianbao
    INTERSPEECH 2022, 2022, : 575 - 579
  • [27] Real-time image carrier generation based on generative adversarial network and fast object detection
    Chuanlong Li
    Xingming Sun
    Zhili Zhou
    Yimin Yang
    Journal of Real-Time Image Processing, 2020, 17 : 655 - 665
  • [28] Upsampling Real-Time, Low-Resolution CCTV Videos Using Generative Adversarial Networks
    Hazra, Debapriya
    Byun, Yung-Cheol
    ELECTRONICS, 2020, 9 (08) : 1 - 20
  • [29] Wasserstein Generative Adversarial Network to Address the Imbalanced Data Problem in Real-Time Crash Risk Prediction
    Man, Cheuk Ki
    Quddus, Mohammed
    Theofilatos, Athanasios
    Yu, Rongjie
    Imprialou, Marianna
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (12) : 23002 - 23013
  • [30] Real-Time Emotion-Based Piano Music Generation Using Generative Adversarial Network (GAN)
    Zheng, Lijun
    Li, Chenglong
    IEEE ACCESS, 2024, 12 : 87489 - 87500