Enis Simsar
I'm a PhD student in Computer Vision and Machine Learning at ETH Zurich currently working on generative models and image editing. I previously did research at Bogazici University working with Prof. Ali Taylan Cemgil on deep generative models. My work focuses on developing novel methods for controllable image generation and editing using diffusion models and GANs.
My recent research has centered on making image editing more precise and intuitive through approaches like attention regularization and contrastive learning. I've developed methods like LIME for localized image editing and UIP2P for unsupervised instruction-based editing. I'm particularly interested in pushing the boundaries of what's possible with generative AI while making these powerful tools more accessible and controllable.
Beyond 2D image generation, I've also worked extensively on 3D-aware generative models and medical imaging applications. I've contributed to projects involving 3D chest CT generation, dental X-ray analysis, and monocular depth estimation. My work aims to bridge the gap between theoretical advances in generative modeling and practical applications that can benefit real-world use cases.
Publications
UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency
Enis Simsar, A. Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
Enis Simsar, Thomas Hofmann, Federico Tombari, Pinar Yanardag
MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
Han Yang, Sotiris Anagnostidis, Enis Simsar, Thomas Hofmann
arXiv.org 2024
PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM
Stefan Stefanache, Llu'is Pastor P'erez, Julen Costa Watanabe, Ernesto Sanchez Tejedor, Thomas Hofmann, Enis Simsar
arXiv.org 2024
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
Matthew Zheng, Enis Simsar, Hidir Yesiltepe, Federico Tombari, Joel Simon, Pinar Yanardag
arXiv.org 2024
CLoRA: A Contrastive Approach to Compose Multiple LoRA Models
Tuna Han Salih Meral, Enis Simsar, Federico Tombari, Pinar Yanardag
arXiv.org 2024
Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography
Ibrahim Ethem Hamamci, Sezgin Er, Furkan Almas, Ayse Gulnihan Simsek, S. Esirgun, Irem Dogan, Muhammed Furkan Dasdelen, Bastian Wittmann, Enis Simsar, Mehmet Simsar, Emine Bensu Erdemir, Abdullah Alanbay, A. Sekuboyina, Berkan Lafci, M. K. Ozdemir, Bjoern H Menze
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
Enis Simsar, A. Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
arXiv.org 2023
CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models
Tuna Han Salih Meral, Enis Simsar, Federico Tombari, Pinar Yanardag
Computer Vision and Pattern Recognition 2023
DENTEX: An Abnormal Tooth Detection with Dental Enumeration and Diagnosis Benchmark for Panoramic X-rays
Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, Atif Emre Yuksel, Sadullah Gultekin, S. Ozdemir, Kai‐Ting Yang, Hongwei Li, Sarthak Pati, B. Stadlinger, A. Mehl, Mustafa Gundogar, Bjoern H Menze
arXiv.org 2023
GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes
Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, A. Sekuboyina, Chinmay Prabhakar, A. Tezcan, Ayse Gulnihan Simsek, S. Esirgun, Furkan Almas, Irem Dougan, Muhammed Furkan Dasdelen, Hadrien Reynaud, Sarthak Pati, Christian Bluethgen, M. K. Ozdemir, Bjoern H Menze
European Conference on Computer Vision 2023
Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, A. Sekuboyina, Mustafa Gundogar, B. Stadlinger, A. Mehl, Bjoern H Menze
International Conference on Medical Image Computing and Computer-Assisted Intervention 2023
LatentSwap3D: Semantic Edits on 3D Image GANs
Enis Simsar, A. Tonioni, Evin Pınar Örnek, F. Tombari
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) 2022
Rank in Style: A Ranking-based Approach to Find Interpretable Directions
Umut Kocasari, Kerem Zaman, Mert Tiftikci, Enis Simsar, Pinar Yanardag
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2022
Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs
Enis Simsar, Umut Kocasari, Ezgi Gulperi Er, Pinar Yanardag
IEEE Workshop/Winter Conference on Applications of Computer Vision 2022
Object-Aware Monocular Depth Prediction With Instance Convolutions
Enis Simsar, Evin Pınar Örnek, Fabian Manhardt, Helisa Dhamo, Nassir Navab, F. Tombari
IEEE Robotics and Automation Letters 2021
Graph2Pix: A Graph-Based Image to Image Translation Framework
Dilara Gokay, Enis Simsar, Efehan Atici, Alper Ahmetoglu, Atif Emre Yuksel, Pinar Yanardag
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) 2021
Dental enumeration and multiple treatment detection on panoramic X-rays using deep learning
Atif Emre Yüksel, Sadullah Gültekin, Enis Simsar, Ş. Özdemir, M. Gündoğar, Salih Barkın Tokgöz, Ibrahim Ethem Hamamci
Scientific Reports 2021
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
Oğuz Kaan Yüksel, Enis Simsar, Ezgi Gulperi Er, Pinar Yanardag
IEEE International Conference on Computer Vision 2021
Comparison of Deep Generative Models for the Generation of Handwritten Character Images
Ömer Kirbiyik, Enis Simsar, Ali Taylan Cemgil
Signal Processing and Communications Applications Conference 2019
GenerateCT: Text-Guided 3D Chest CT Generation
Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, A. Tezcan, Aysegul Simsek, Furkan Almas, S. Esirgun, Hadrien Reynaud, Sarthak Pati, Christian Blüthgen, Bjoern H Menze
arXiv.org 2023
