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
  • [31] Research on real-time optimization control algorithm of cement burning system based on Generative Adversarial Network
    Zhang Cheng-Wei
    Li Hui-Xia
    Wang Lei
    Zhou Qiang
    Han Liang
    Weng Si-Hao
    Wu Yan-Wen
    ZKG INTERNATIONAL, 2023, 76 (08): : 48 - 55
  • [32] GANTL: Toward Practical and Real-Time Topology Optimization With Conditional Generative Adversarial Networks and Transfer Learning
    Behzadi, Mohammad Mahdi
    Ilies, Horea T.
    JOURNAL OF MECHANICAL DESIGN, 2022, 144 (02)
  • [33] Generative adversarial network for real-time identification and pixel-level annotation of highway pavement distresses
    Amo-Boateng, Mark
    Adu-Gyamfi, Yaw
    AUTOMATION IN CONSTRUCTION, 2025, 174
  • [34] A real-time flow forecasting with deep convolutional generative adversarial network: Application to flooding event in Denmark
    Cheng, Meiling
    Fang, Fangxin
    Navon, I. M.
    Pain, C. C.
    PHYSICS OF FLUIDS, 2021, 33 (05)
  • [35] Lightweight actor-critic generative adversarial networks for real-time smart generation control of microgrids
    Han, Kunlun
    Yang, Kai
    Yin, Linfei
    APPLIED ENERGY, 2022, 317
  • [36] Robust real-time energy management for a hydrogen refueling station using generative adversarial imitation learning
    Huy, Truong Hoang Bao
    Duy, Nguyen Thanh Minh
    Phu, Pham Van
    Le, Tien-Dat
    Park, Seongkeun
    Kim, Daehee
    APPLIED ENERGY, 2024, 373
  • [37] Time-domain speech enhancement using generative adversarial networks
    Pascual, Santiago
    Serra, Joan
    Bonafonte, Antonio
    SPEECH COMMUNICATION, 2019, 114 : 10 - 21
  • [38] Real-time anomaly detection for ‘Remote’ bus stop surveillance using unsupervised conditional generative adversarial networks
    Xi B.
    Chen Q.
    Neural Computing and Applications, 2024, 36 (25) : 15799 - 15813
  • [39] FDC Real-time Monitor Enhancement
    Chu, Jade
    2011 INTERNATIONAL SYMPOSIUM ON SEMICONDUCTOR MANUFACTURING (ISSM) AND E-MANUFACTURING AND DESIGN COLLABORATION SYMPOSIUM (EMDC), 2011,
  • [40] REAL-TIME OPTICAL EDGE ENHANCEMENT
    LEWIS, RW
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA, 1976, 66 (10) : 1127 - 1127