Akhmedkhan (Ahan) Shabanov
Hi! I am a PhD student at the GrUVi lab of SFU advised by Andrea Tagliasacchi in a beautiful Vancouver. I work on 3D computer vision.
Previously, I was a research engineer (founding team member) at Avaturn (ex. In3D) working with Dmitry Ulyanov on 3D human body and face reconstruction from in-the-wild images. Even before that, I received my BSc and MSc degrees from Moscow Institute of Physics and Technology in applied mathematics and physics.
News
Publications
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.