Research
I'm interested in image synthesis, and particularly, controlled image synthesis.
There are multiple ways to gain control over the image generation process such as conditioning or learning disentangled representations.
I'm also interested in automatic evaluation techniques for vision & language systems which is a challenging problem.
If you are interested in similar topics, want to chat or collaborate, feel free to contact me.
|
|
DT2I: Dense Text-to-Image Generation from Region Descriptions
Stanislav Frolov*, Prateek Bansal*, Jörn Hees, Andreas Dengel
arXiv, 2022
|
|
Combining Transformer Generators with Convolutional Discriminators
Ricard Durall*, Stanislav Frolov*, Jörn Hees, Federico Raue, Franz-Josef Pfreundt, Andreas Dengel, Janis Keuper
GCAI, 2021
|
|
AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style
Stanislav Frolov, Avneesh Sharma, Jörn Hees, Tushar Karayil, Federico Raue, Andreas Dengel
GCPR, 2021
code
|
|
Adversarial Text-to-Image Synthesis: A Review
Stanislav Frolov, Tobias Hinz, Federico Raue, Jörn Hees, Andreas Dengel
Neural Networks Journal, 2021
|
|
Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching
Fatemeh Azimi, Stanislav Frolov, Federico Raue, Jörn Hees, Andreas Dengel
VISIGRAPP, 2021
code
|
|
Leveraging Visual Question Answering to Improve Text-to-Image Synthesis
Stanislav Frolov, Shailza Jolly, Jörn Hees, Andreas Dengel
LANTERN workshop at COLING, 2020
slides
|
|