About
Publications
⇆ Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
Massimiliano Viola Kevin Qu Nando Metzger Bingxin Ke Alexander Becker Konrad Schindler Anton Obukhov
Preprint, under review
🛹 RollingDepth 🛹: Video Depth without Video Models
Bingxin Ke Dominik Narnhofer Shengyu Huang Lei Ke Torben Peters Katerina Fragkiadaki Anton Obukhov Konrad Schindler
Preprint, under review
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Yuru Jia Lukas Hoyer Shengyu Huang Tianfu Wang Luc Van Gool Konrad Schindler Anton Obukhov
European Conference on Computer Vision (ECCV) 2024
Marigold Depth: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke Anton Obukhov Shengyu Huang Nando Metzger Rodrigo Caye Daudt Konrad Schindler
📣 Oral talk at the Conference on Computer Vision and Pattern Recognition (CVPR) 2024
💎 Best Paper Award Candidate
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Xiang Zhang Bingxin Ke Hayko Riemenschneider Nando Metzger Anton Obukhov Markus Gross Konrad Schindler Christopher Schroers
Conference on Neural Information Processing Systems (NeurIPS) 2024
Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds
Yujia Liu Anton Obukhov Jan Dirk Wegner Konrad Schindler
ISPRS Journal of Photogrammetry and Remote Sensing
Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds
Yujia Liu Anton Obukhov Jan Dirk Wegner Konrad Schindler
🔦 Spotlight talk at the Conference on Computer Vision and Pattern Recognition (CVPR) 2024
I-Design: Personalized LLM Interior Designer
Ata Çelen Guo Han Konrad Schindler Luc Van Gool Iro Armeni Anton Obukhov Xi Wang
Preprint, under review
Breathing New Life into 3D Assets with Generative Repainting
Tianfu Wang Menelaos Kanakis Konrad Schindler Luc Van Gool Anton Obukhov
🦄 Oral talk at the British Machine Vision Conference (BMVC) 2023
DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models
International Conference on Computer Vision (ICCV) 2023
TT-NF: Tensor Train Neural Fields
IEEE Journal of Selected Topics in Signal Processing
Spectral Tensor Train Parameterization of Deep Learning Layers
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
T-Basis: a Compact Representation for Neural Networks
International Conference on Machine Learning (ICML) 2020
News
- 2025.01: I am co-organizing the Monocular Depth Estimation Challenge (MDEC) at CVPR 2025.
- 2024.11: I was honored to deliver an invited talk at the DA-Z 2024 conference, organized by DA/S Digital Art and Science Switzerland, on the progress of our research team focusing on repurposing generative AI for computer vision at the Photogrammetry and Remote Sensing Lab of ETH Zürich. Additionally, I participated in a panel discussion titled “GenAI: Facilitator or Disruptor of Our Future?”
- 2024.10: I joined the Bayer Lab at Huawei Research Center Zürich as a Principal Research Scientist to work on computer vision for phone cameras.
- 2024.09: One paper was accepted at NeurIPS 2024: “BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation.”
- 2024.07: One paper was accepted at ECCV 2024: “DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control.”
- 2024.07: One paper was accepted at ISPRS Journal of Photogrammetry and Remote Sensing: “Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds.”
- 2024.05: I contributed Marigold pipelines into diffusers 🧨, the main open-source codebase of visual GenAI.
- 2024.05: I was honored to be an invited speaker at the GenAI Zürich conference with a talk titled "Beyond Astronaut on a Horse: Repurposing Text-to-Image Diffusion Models".
- 2024.04: One paper was accepted at CVPR 2024 Workshop on Synthetic Data for Computer Vision: "DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control."
- 2024.04: One paper was accepted at CVPR 2024 Workshop on AI for 3D Generation: "Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models."
- 2024.04: One paper was accepted at CVPR 2024 Workshop on Urban Scene Modeling: Where Vision Meets Photogrammetry and Graphics: "Point2Building: Reconstructing Buildings from airborne LiDAR Point Clouds."
- 2024.02: Two papers were accepted at CVPR 2024, one Oral “Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation.” and one Spotlight “Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds”.
- 2023.09: One paper was accepted at BMVC 2023 as Oral: “Breathing New Life into 3D Assets with Generative Repainting.”
- 2023.07: Two papers were accepted at ICCV 2023: “DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models” and “EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation.”
- 2023.04: One paper was accepted at CVPR 2023 Workshop on Structural and Compositional Learning on 3D Data: “Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds.”
- 2023.03: One paper was accepted at ICLR 2023 Workshop on Neural Fields: “TT-NF: Tensor Train Neural Fields.”
- 2022.11: One paper was accepted at SlowDNN 2023 Workshop on Low-dimensionality in Deep Neural Networks: “TT-NF: Tensor Train Neural Fields.”
- 2022.11: I gave an invited talk at Huawei Research Center Zürich about our latest work, “TT-NF: Tensor Train Neural Fields.”
- 2022.11: I started as a postdoc in the Photogrammetry and Remote Sensing Group at ETH Zürich with Professor Konrad Schindler.
- 2022.09: I successfully defended my Ph.D. thesis titled “Tensor Decompositions in Deep Learning.”
- 2022.08: One paper was accepted at NeurIPS 2022: “Towards Practical Control of Singular Values of Convolutional Layers.”
- 2022.07: I attended ICVSS summer school 2022.
- 2022.06: Two patents were published based on the AISTATS 2021 paper “Spectral Tensor Train Parameterization of Deep Learning Layers.”
- 2022.03: One paper was accepted at CVPR 2022: “Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translation.”
- 2021.12: One patent was published based on the ICML 2020 paper “T-Basis: a Compact Representation for Neural Networks.”
- 2021.07: One paper was accepted at ICCV 2021: “Exploring Relational Context for Multi-Task Dense Prediction.”
- 2021.06: One paper was accepted at Workshop on Sparsity in Neural Networks: “Spectral Tensor Train Parameterization of Deep Learning Layers.”
- 2021.03: One paper was accepted at CVPR 2021: “Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation.”
- 2021.04: torch-fidelity will be featured at PyTorch Ecosystem Day 2021.
- 2021.01: One paper was accepted at AISTATS 2021: “Spectral Tensor Train Parameterization of Deep Learning Layers.”
- 2020.07: One paper was accepted at ECCV 2020: “Reparameterizing Convolutions for Incremental Multi-task Learning without Task Interference”.
- 2020.06: One paper was accepted at ICML 2020: “T-Basis: a Compact Representation for Neural Networks.”
- 2018.05: I started as a Ph.D. candidate in the Computer Vision Lab at ETH Zürich with Professor Luc Van Gool.