Anton Obukhov
Scholar

Anton Obukhov

Google Scholar ID: EyE8nngAAAAJ
Principal Research Scientist, Huawei Research Center Zürich
Computer VisionGenerative AI
Citations & Impact
All-time
Citations
1,635
 
H-index
15
 
i10-index
22
 
Publications
20
 
Co-authors
50
list available
Resume (English only)
Academic Achievements
  • Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis, IEEE TPAMI 2025.
  • Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion, ICCV 2025.
  • RollingDepth: Video Depth without Video Models, CVPR 2025.
  • DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control, ECCV 2024.
  • Marigold Depth: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation, CVPR 2024 (Oral, Best Paper Award Candidate).
  • BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation, NeurIPS 2024.
  • Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds, ISPRS Journal.
  • Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds, CVPR 2024 (Spotlight).
  • I-Design: Personalized LLM Interior Designer, ECCV 2024 Workshop CV4Metaverse.
  • Breathing New Life into 3D Assets with Generative Repainting, BMVC 2023 (Oral).
  • EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation, ICCV 2023.
  • DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models, ICCV 2023.
  • TT-NF: Tensor Train Neural Fields