TOBIAS HINZ

      Avatar

      Machine Learning

      Research Engineer

      Adobe Research

    I am a machine learning reseach engineer at Adobe Research in California, working on generative models for image generation and editing. I am interested in using generative models that allow conditional and unconditional generation and editing of images. I am also interested in few-shot learning and the automatic evaluation of generative models.

    I obtained my PhD at the Knowledge Technology group at the University of Hamburg (Germany). Before that, I completed a research oriented Master's degree in Intelligent Adaptive Systems at the University of Hamburg. I received a Bachelor's degree in Business Informatics at the University of Mannheim, during which I also studied at the National University of Singapore for one semester.

News

  • 05/2022: Our paper on transformers for image editing has been accepted to SIGGRAPH 2022.
  • 05/2022: I have moved to San Jose (California) to join the Adobe Headquarters office.
  • 01/2022: Our paper won the Best Application Paper award at WACV 2022.
  • 09/2021: Our review paper on adversarial text-to-image synthesis has been published by the Neural Networks Journal.
  • 08/2021: Check out this concert which combines music with generated videos. Our ConSinGAN approach was used in the video for "Robbie's Hobbies.
  • 04/2021: I successfully defended my PhD thesis.
  • 02/2021: Have a look at our paper on Few-Shot Character Animation (code available).
  • 01/2021: Check out our latest review paper on Adversarial Text-to-Image Synthesis.
  • 01/2021: I started a new position as machine learning research engineer with Adobe Research.
  • 11/2020: Our work on Single-Image GANs (code available) got accepted to WACV 2021.

Selected Publications

For a full list, have a look at my Google Scholar page.


      ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions

      A neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map.

      D. Liu, S. Shetty, T. Hinz, M. Fisher, R. Zhang, T. Park, E. Kalogerakis, ACM Transactions on Graphics (SIGGRAPH 2022) 2022.


      CharacterGAN: Few-Shot Keypoint Character Animation and Reposing

      BEST PAPER AWARD - Train a GAN on as few as 10 images of a given character for animation and reposing.

      T. Hinz, M. Fisher, O. Wang, E. Shechtman, S. Wermter, IEEE Winter Conference on Applications of Computer Vision 2022.


      Improved Techniques for Training Single-Image GANs

      Improving the results and training speed of single-image GANs.

      T. Hinz, M. Fisher, O. Wang, S. Wermter, IEEE Winter Conference on Applications of Computer Vision 2021.


      Semantic Object Accuracy for Generative Text-to-Image Synthesis

      A novel GAN architecture and an improved metric to evaluate generative text-to-image synthesis models.

      T. Hinz, S. Heinrich, S. Wermter, IEEE Transactions on Pattern Analysis and Machine Intelligence 2020.


      Generating Multiple Objects at Spatially Distinct Locations

      Fine-grained control over the placement and identity of objects in images generated with a Generative Adversarial Network.

      T. Hinz, S. Heinrich, S. Wermter, International Conference on Learning Representations 2019.


      Speeding Up the Hyperparameter Optimization Of Deep Convolutional Neural Networks

      How to use lower dimensional data representations to speed up the hyperparameter optimization for CNNs processing images..

      T. Hinz, N. Navarro-Guerrero, S. Magg, S. Wermter, International Journal of Computational Intelligence and Applications 2018.



See All

See All

Curriculum Vitae