3D Volumetric Modeling with Introspective Neural Networks


  • Wenlong Huang University of California, Berkeley
  • Brian Lai University of California, Los Angeles
  • Weijian Xu University of California San Diego
  • Zhuowen Tu University of California San Diego




In this paper, we study the 3D volumetric modeling problem by adopting the Wasserstein introspective neural networks method (WINN) that was previously applied to 2D static images. We name our algorithm 3DWINN which enjoys the same properties as WINN in the 2D case: being simultaneously generative and discriminative. Compared to the existing 3D volumetric modeling approaches, 3DWINN demonstrates competitive results on several benchmarks in both the generation and the classification tasks. In addition to the standard inception score, the Frechet Inception Distance (FID) metric is´ also adopted to measure the quality of 3D volumetric generations. In addition, we study adversarial attacks for volumetric data and demonstrate the robustness of 3DWINN against adversarial examples while achieving appealing results in both classification and generation within a single model. 3DWINN is a general framework and it can be applied to the emerging tasks for 3D object and scene modeling.1




How to Cite

Huang, W., Lai, B., Xu, W., & Tu, Z. (2019). 3D Volumetric Modeling with Introspective Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8481-8488. https://doi.org/10.1609/aaai.v33i01.33018481



AAAI Technical Track: Vision