Fereshteh Forghani

I am a Researcher at the York University in CVIL Lab supervised by Dr. Kosta Derpanis.

I recived my Master's of Science in Computer Science supervised by Dr. Marcus Brubaker. During my Master's, I was a research intern with at the Vector Institute, where I worked closely with Arash Afkanpour.

Previously, I received my Bachelor of Science in Computer Engineering from Sharif University of Technology. During the final summer of my bachelor's program, I was an intern at EPFL where I worked in VITALAB under the supervision of Prof. Alex Alahi.

My research interests lie in the intersection of 3D computer vision, generative modeling, and machine learning.

Email / CV / Google Scholar / Github / Twitter / LinkedIn

News

07/2025: Attended International Computer Vision Summer School (ICVSS) in Sicily.
07/2024: "PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis" has been accepted to ECCV 2024.
01/2024: Started my internship at Vector Institute.
07/2023: "Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models" has been accepted to ICCV 2023.
07/2023: I participated in DLRL summer school at Mila.

Publications & Preprints

	Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis Fereshteh Forghani, Jason J. Yu, Tristan Aumentado-Armstrong, Konstantinos G. Derpanis, Marcus A. Brubaker, ArXiv 2025 (in submission) project page / arXiv We propose a framework to estimate scene scales jointly with the GNVS model in an end-to-end fashion. We also define two new metrics, Sample Flow Variability (SFV) and Scale-Sensitive Thresholded Symmetric Epipolar Distance (SS-TSED),that directly measure the variability of scale learned by a GNVS method.
	Can Generative Models Improve Self-Supervised Representation Learning? Sana Ayromlou, Vahid Reza Khazaie, Fereshteh Forghani, Arash Afkanpour, AAAI 2025 arXiv we introduce a framework that enriches the self-supervised learning (SSL) paradigm by utilizing generative models to produce semantically consistent image augmentations. By directly conditioning generative models on a source image, our method enables the generation of diverse augmentations while maintaining the semantics of the source image, thus offering a richer set of data for SSL.
	PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis Jason J. Yu, Tristan Aumentado-Armstrong, Fereshteh Forghani, Konstantinos G. Derpanis, Marcus A. Brubaker, ECCV 2024 project page / arXiv / code we propose a set-based generative model that can simultaneously generate multiple, self-consistent new views, conditioned on any number of views. Our approach is not limited to generating a single image at a time and can condition on a variable number of views. As a result, when generating a large number of views, our method is not restricted to a low-order autoregressive generation approach and is better able to maintain generated image quality over large sets of images.
	Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models Jason J. Yu, Fereshteh Forghani, Konstantinos G. Derpanis, Marcus A. Brubaker, ICCV 2023 project page / arXiv / code we propose a novel generative model capable of producing a sequence of photorealistic images consistent with a specified camera trajectory, and a single starting image. To measure the consistency over a sequence of generated views, we introduce a new metric, the thresholded symmetric epipolar distance (TSED), to measure the number of consistent frame pairs in a sequence.

Design and source code from Jon Barron's website.