Style Agnostic 3D Reconstruction via Adversarial Style Transfer

被引:0
|
作者
Petersen, Felix [1 ]
Goldluecke, Bastian [1 ]
Deussen, Oliver [1 ]
Kuehne, Hilde [2 ,3 ]
机构
[1] Univ Konstanz, Constance, Germany
[2] Goethe Univ Frankfurt, Frankfurt, Germany
[3] IBM MIT Watson AI Lab, Cambridge, MA USA
关键词
D O I
10.1109/WACV51458.2022.00233
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Reconstructing the 3D geometry of an object from an image is a major challenge in computer vision. Recently introduced differentiable renderers can be leveraged to learn the 3D geometry of objects from 2D images, but those approaches require additional supervision to enable the renderer to produce an output that can be compared to the input image. This can be scene information or constraints such as object silhouettes, uniform backgrounds, material, texture, and lighting. In this paper, we propose an approach that enables a differentiable rendering-based learning of 3D objects from images with backgrounds without the need for silhouette supervision. Instead of trying to render an image close to the input, we propose an adversarial style-transfer and domain adaptation pipeline that allows to translate the input image domain to the rendered image domain. This allows us to directly compare between a translated image and the differentiable rendering of a 3D object reconstruction in order to train the 3D object reconstruction network. We show that the approach learns 3D geometry from images with backgrounds and provides a better performance than constrained methods for single-view 3D object reconstruction on this task.
引用
收藏
页码:2273 / 2282
页数:10
相关论文
共 50 条
  • [41] TACHIEGAN: GENERATIVE ADVERSARIAL NETWORKS FOR TACHIE STYLE TRANSFER
    Chen, Zihan
    Chen, Xuejin
    2022 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (IEEE ICMEW 2022), 2022,
  • [42] Multitask Adversarial Learning for Chinese Font Style Transfer
    Wu, Lei
    Chen, Xi
    Meng, Lei
    Meng, Xiangxu
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [43] Face Style Transfer and Removal with Generative Adversarial Network
    Zhu, Qiang
    Li, Ze-Nian
    PROCEEDINGS OF MVA 2019 16TH INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA), 2019,
  • [44] Adversarial Example Generation Method Based on Style Transfer
    Yu, Zhcnhua
    Yin, Zheng
    Ye, Ou
    Cong, Xuya
    Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University, 2024, 58 (07): : 191 - 202
  • [45] StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields
    Liu, Kunhao
    Zhan, Fangneng
    Chen, Yiwen
    Zhang, Jiahui
    Yu, Yingchen
    El Saddik, Abdulmotaleb
    Lu, Shijian
    Xing, Eric
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 8338 - 8348
  • [46] Painting style transfer and 3D interaction by model-based image synthesis
    Chen, Tian-Ding
    PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2008, : 2976 - 2981
  • [47] Artistic image adversarial attack via style perturbation
    Haiyan Zhang
    Quan Wang
    Guorui Feng
    Multimedia Systems, 2023, 29 (6) : 3745 - 3755
  • [48] Style Separation and Synthesis via Generative Adversarial Networks
    Zhang, Rui
    Tang, Sheng
    Li, Yu
    Guo, Junbo
    Zhang, Yongdong
    Li, Jintao
    Yan, Shuicheng
    PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 183 - 191
  • [49] Artistic image adversarial attack via style perturbation
    Zhang, Haiyan
    Wang, Quan
    Feng, Guorui
    MULTIMEDIA SYSTEMS, 2023, 29 (06) : 3745 - 3755
  • [50] Image Style Transfer via Multi-Style Geometry Warping
    Alexandru, Ioana
    Nicula, Constantin
    Prodan, Cristian
    Rotaru, Razvan-Paul
    Tarba, Nicolae
    Boiangiu, Costin-Anton
    APPLIED SCIENCES-BASEL, 2022, 12 (12):