Akhmedkhan (Ahan) Shabanov
Hi! I’m a PhD student at Simon Fraser University in Vancouver, advised by Andrea Tagliasacchi. I work on 3D computer vision.
During my PhD, I spent time as a research intern at Meta in Zurich, focusing on generative 3D reconstruction. Before that, I was a research engineer and founding member at Avaturn, collaborating with Dmitry Ulyanov on 3D human body and face reconstruction from in-the-wild images. Earlier, I did my BSc and MSc in Applied Mathematics and Physics at the Moscow Institute of Physics and Technology.
News
Publications
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Ahan Shabanov, Peter Hedman, Ethan Weber, Zhengqin Li, Denis Rozumny, Gael Le Lan, Naina Dhingra, Lei Luo, Andrea Vedaldi, Christian Richardt, Andrea Tagliasacchi, Bo Zhu, Numair Khan
ECCV 2026
Flow matching directly over 3D Gaussian parameters turns sparse-view reconstruction into a generative process that can synthesize plausible content in unobserved regions.
BANF: Band-limited Neural Fields for Levels of Detail Reconstruction
Ahan Shabanov, Shrisudhan Govindarajan, Cody Reading, Lily Goli, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
CVPR 2024
We explore how a simple modification to neural fields enables low-pass filtering, facilitating improved frequency decomposition which is crucial for level-of-detail reconstruction.
Lagrangian Hashing for Compressed Neural Field Representations
Shrisudhan Govindarajan, Zeno Sambugaro, Ahan Shabanov, Towaki Takikawa, Weiwei Sun, Daniel Rebain, Nicola Conci, Kwang Moo Yi, Andrea Tagliasacchi
ECCV 2024
A representation for neural fields combining the characteristics of Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF).
Self-supervised Depth Denoising Using Lower- and Higher-quality RGB-D sensors
Ahan Shabanov, Ilya Krotov, Nikolay Chinaev, Vsevolod Poletaev, Sergei Kozlukov, Igor Pasechnik, Bulat Yakupov, Artsiom Sanakoyeu, Vadim Lebedev, Dmitry Ulyanov
3DV, 2020
Denoising iPhone's depth images by using Kinect depth sensor
Unsupervised temporal consistency improvement for microscopy video segmentation with Siamese networks
Ahan Shabanov, Daja Schichler, Constantin Pape, Sara Cuylen-Haering, Anna Kreshuk
BioRxiv, 2021
We enhance video segmentation by re-training a CNN in a Siamese setup, optimizing both accuracy on labeled images and consistency across unlabeled frames.
In-the-wild 3D head reconstruction
US Patent; 2022
A production-oriented system for reconstructing detailed 3D head geometry and hair from unconstrained multi-view images, designed to stay robust under real-world capture conditions.