Anton Obukhov

ETH Zurich — Switzerland

Computer Science · Physical Sciences

13h-index608citations47works13.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(9), Advanced Vision and Imaging(9), Domain Adaptation and Few-Shot Learning(8), Computer Graphics and Visualization Techniques(7), 3D Shape Modeling and Analysis(6)

Publications47 total

torch-fidelity: High-fidelity performance metrics for generative models in PyTorch
Zenodo (CERN European Organization for Nuclear Research)·2026Open Access
torch-fidelity: High-fidelity performance metrics for generative models in PyTorch
Zenodo (CERN European Organization for Nuclear Research)·2026Open Access
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
arXiv (Cornell University)·2025Open Access
Reflection Removal through Efficient Adaptation of Diffusion Transformers
arXiv (Cornell University)·2025Open Access
The Methodology of Penetration Testing using Artificial Intelligence Technology
2025
The Fourth Monocular Depth Estimation Challenge
2025· 2 cited
Video Depth without Video Models
2025· 5 cited
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
arXiv (Cornell University)·2025Open Access
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
Repository for Publications and Research Data (ETH Zurich)·2025Open Access
The Fourth Monocular Depth Estimation Challenge
arXiv (Cornell University)·2025Open Access
I-Design: Personalized LLM Interior Designer
Lecture notes in computer science·2025· 10 cited
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 3 cited
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
Repository for Publications and Research Data (ETH Zurich)·2025Open Access
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
arXiv (Cornell University)·2024Open Access
Video Depth without Video Models
arXiv (Cornell University)·2024Open Access
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Lecture notes in computer science·2024· 17 cited
TT-NF: Tensor Train Neural Fields
IEEE Journal of Selected Topics in Signal Processing·2024
Point2Building: Reconstructing buildings from airborne LiDAR point clouds
ISPRS Journal of Photogrammetry and Remote Sensing·2024· 19 citedOpen Access
NTIRE 2024 Challenge on HR Depth from Images of Specular and Transparent Surfaces
2024· 21 cited
Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models
arXiv (Cornell University)·2024Open Access
page 1 of 3Next →

Frequent Co-authors

Konrad Schindler(22), Luc Van Gool(20), Bingxin Ke(10), Dengxin Dai(8), Shengyu Huang(7), Nando Metzger(7), Stamatios Georgoulis(7), Tianfu Wang(6), Menelaos Kanakis(6), Shengqu Cai(4), Jan Dirk Wegner(4), Fabio Tosi(4), Matteo Poggi(4), Lukas Hoyer(4), Yujia Liu(3), Suman Saha(3), Maxim Rakhuba(3), Rodrigo Caye Daudt(2), Eric Ryan Chan(2), Songyou Peng(2)