Mohamad Shahbazi

About Me

I am a PhD candidate at Computer Vision Lab, ETH Zurich, under the supervision of Prof. Luc Van Gool. My research interests mainly include Machine Learning and Computer Vision.

Research Interests

• Computer Vision
• Generative Models
• Neural Rendering
• Vision-Language Models

Experiences

• Internship at Microsoft UK 01/2024 - Current
• Research Internship at Google Switzerland 06/2023 - 09/2023
  Worked on 3D editing of 3D scenes using Diffusion Models and Neural Radiance Fields.

Publications

• InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
  M. Shahbazi*, L. Claessens*, M. Niemeyer, E. Collins, A. Tonioni, L. Van Gool, F. Tombari.
  Under review
  Paper
• StyleGenes: Discrete and Efficient Latent Distributions for GANs
  E. Ntavelis, M. Shahbazi, I. Kastanis, M. Danelljan, L. Van Gool.
  WACV 2024
  Paper
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
  M. Shahbazi, E. Ntavelis, A. Tonioni, E. Collins, D. P. Paudel, M. Danelljan, L. Van Gool.
  ICCVW 2023
  Paper | Code
• Diffdreamer: Towards consistent unsupervised single-view scene extrapolation with conditional diffusion models
  S. Cai, E. R. Chan, S. Peng, M. Shahbazi, A. Obukhov, L. Van Gool, G. Wetzstein.
  ICCV 2023
  Paper | Project Page | Code |
• A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials
  C. Li, Z. Huang, D. P. Paudel, Y. Wang, M. Shahbazi, X. Hong, L. Van Gool.
  WACV 2023
  Paper | Code
• Training Dynamics Aware Neural Network Optimization with Stabilization
  Z. Fang, M. Shahbazi, T. Probst, D. P. Paudel, L. Van Gool.
  ACCV 2023
  Paper | Code
• Arbitrary-scale image synthesis
  E. Ntavelis, M. Shahbazi, I. Kastanis, R. Timofte, M. Danelljan, L. Van Gool.
  CVPR 2022
  Paper | Code
• Collapse by conditioning: Training class-conditional GANs with limited data
  M. Shahbazi, M. Danelljan, D. P. Paudel, L. Van Gool.
  ICLR 2022
  Paper | Code
• Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
  M. Shahbazi, Z. Huang, D. P. Paudel, A. Chhatkuli, L. Van Gool.
  CVPR 2021
  Paper | Code
• A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture
  M. Shahbazi, H. Aghajan.
  IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 2018
  Paper

Tweets by MShahbazi_