Nikita Araslanov

I'm a postdoc in the Computer Vision Group at TU Munich and a visiting faculty at Google. I'm interested in semantic and 3D-based visual inference from video data. Previously, I completed a PhD in the Visual Inference Lab at TU Darmstadt. I obtained my master's in Computer Science from University of Bonn. I also hold a Diploma degree in Mechanical Engineering from Moscow Aviation Institute (specialising in jets).

26/06/2025 Introducing BA-Track: dynamic scene reconstruction with bundle adjustment. Accepted at ICCV 2025.
26/02/2025 Two papers accepted at CVPR 2025! Code and preprints will be available soon.
15/12/2024 I joined Google as a visiting faculty researcher.
11/09/2024 Oral presentation at GCPR: CARLA Drone, a synthetic dataset for drone-view 2D/3D object detection and more.
03/07/2024 Introducing DiffCD: an SDF-based shape reconstruction approach from point clouds. To be presented at ECCV '24!

Practical Course

(SS25) Deep Learning for Spatial AI

Course page

Lecture

(WS24/25) Computer Vision 3: Segmentation, Detection and Tracking

Course details

	New!Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi and Daniel Cremers International Conference on Computer Vision (ICCV), 2025, to appear Paper (arXiv) \| Project webpage
	New!It’s a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Dominik Schnaus, Nikita Araslanov and Daniel Cremers Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Paper (arXiv) \| Code \| Project webpage
	New!Scene-Centric Unsupervised Panoptic Segmentation Oliver Hahn^, Christoph Reich^, Nikita Araslanov, Daniel Cremers, Christian Rupprecht and Stefan Roth Conference on Computer Vision and Pattern Recognition (CVPR), 2025 highlight Paper \| Code \| Project webpage
	CARLA Drone: Monocular 3D Object Detection from a Different Perspective Johannes Meier, Luca Scalerandi, Oussema Dhaouadi, Jacques Kaiser, Nikita Araslanov and Daniel Cremers DAGM German Conference on Pattern Recognition (GCPR), 2024 oral Paper (arXiv) \| Project webpage
	DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting Linus Härenstam-Nielsen, Lu Sang, Abhishek Saroha, Nikita Araslanov and Daniel Cremers European Conference on Computer Vision (ECCV), 2024 Paper (arXiv) \| Code
	Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer and Stefan Roth Transactions on Machine Learning Research (TMLR), 2024 Paper \| Code
	Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball Simon Weber, Barış Zöngür, Nikita Araslanov and Daniel Cremers Conference on Computer Vision and Pattern Recognition (CVPR), 2024 Paper (arXiv) \| Code
	An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment Sergei Solonets^, Daniil Sinitsyn^, Lukas Von Stumberg, Nikita Araslanov and Daniel Cremers International Conference on Learning Representations (ICLR), 2024 oral Paper \| Code

	New!Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi and Daniel Cremers International Conference on Computer Vision (ICCV), 2025, to appear Paper (arXiv) \| Project webpage
	New!It’s a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Dominik Schnaus, Nikita Araslanov and Daniel Cremers Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Paper (arXiv) \| Code \| Project webpage
	New!Scene-Centric Unsupervised Panoptic Segmentation Oliver Hahn^, Christoph Reich^, Nikita Araslanov, Daniel Cremers, Christian Rupprecht and Stefan Roth Conference on Computer Vision and Pattern Recognition (CVPR), 2025 highlight Paper \| Code \| Project webpage
	CARLA Drone: Monocular 3D Object Detection from a Different Perspective Johannes Meier, Luca Scalerandi, Oussema Dhaouadi, Jacques Kaiser, Nikita Araslanov and Daniel Cremers DAGM German Conference on Pattern Recognition (GCPR), 2024 oral Paper (arXiv) \| Project webpage
	DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting Linus Härenstam-Nielsen, Lu Sang, Abhishek Saroha, Nikita Araslanov and Daniel Cremers European Conference on Computer Vision (ECCV), 2024 Paper (arXiv) \| Code
	Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer and Stefan Roth Transactions on Machine Learning Research (TMLR), 2024 Paper \| Code
	Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball Simon Weber, Barış Zöngür, Nikita Araslanov and Daniel Cremers Conference on Computer Vision and Pattern Recognition (CVPR), 2024 Paper (arXiv) \| Code
	An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment Sergei Solonets^, Daniil Sinitsyn^, Lukas Von Stumberg, Nikita Araslanov and Daniel Cremers International Conference on Learning Representations (ICLR), 2024 oral Paper \| Code

About

News

Teaching

Recent Publications (Google Scholar )

New!Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

New!It’s a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data

New!Scene-Centric Unsupervised Panoptic Segmentation

CARLA Drone: Monocular 3D Object Detection from a Different Perspective

DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting

Boosting Unsupervised Semantic Segmentation
with Principal Mask Proposals

Flattening the Parent Bias:
Hierarchical Semantic Segmentation in the Poincaré Ball

An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment