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
  • [31] Arbitrary style transfer via content consistency and style consistency
    Xiaoming Yu
    Gan Zhou
    The Visual Computer, 2024, 40 : 1369 - 1382
  • [32] Ethnic Style Representation Learning for Single-View 3D Garment Reconstruction
    Zhang Y.
    Liu L.
    Fu X.
    Liu L.
    Peng W.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2024, 36 (02): : 258 - 272
  • [33] Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
    Ge, Zhijin
    Shang, Fanhua
    Liu, Hongying
    Liu, Yuanyuan
    Wan, Liang
    Feng, Wei
    Wang, Xiaosen
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 4440 - 4449
  • [34] Evolvement Constrained Adversarial Learning for Video Style Transfer
    Li, Wenbo
    Wen, Longyin
    Bian, Xiao
    Lyu, Siwei
    COMPUTER VISION - ACCV 2018, PT I, 2019, 11361 : 232 - 248
  • [35] Generative Adversarial Style Transfer Networks for Face Aging
    Palsson, Sveinn
    Agustsson, Eirikur
    Timofte, Radu
    Van Gool, Luc
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 2165 - 2173
  • [36] RL-VAEGAN: Adversarial defense for reinforcement learning agents via style transfer
    Hu, Yueyue
    Sun, Shiliang
    KNOWLEDGE-BASED SYSTEMS, 2021, 221
  • [37] Stain Style Transfer Using Transitive Adversarial Networks
    Cai, Shaojin
    Xue, Yuyang
    Gao, Qinquan
    Du, Min
    Chen, Gang
    Zhang, Hejun
    Tong, Tong
    MACHINE LEARNING FOR MEDICAL IMAGE RECONSTRUCTION, MLMIR 2019, 2019, 11905 : 163 - 172
  • [38] A Geometrical Perspective on Image Style Transfer With Adversarial Learning
    Pan, Xudong
    Zhang, Mi
    Ding, Daizong
    Yang, Min
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (01) : 63 - 75
  • [39] Image Style Transfer based on Generative Adversarial Network
    Hu, Chan
    Ding, Youdong
    Li, Yuhang
    PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020), 2020, : 2098 - 2102
  • [40] A Survey of Style Transfer Based on Generative Adversarial Network
    Qin, Ming-yu
    Fan, You-chen
    Liu, Bao-lin
    Ma, Xu
    AOPC 2021: NOVEL TECHNOLOGIES AND INSTRUMENTS FOR ASTRONOMICAL MULTI-BAND OBSERVATIONS, 2021, 12069