4D and Quantum Computer Vision Group

Visual Computing and Artificial Intelligence Department

12.06.25: [New] N. Kairanda invited to give a talk at the CVPR 2025 Workshop on Vision Meets Physics.
12.06.25: [New] Invited Talk at the CVPR 2025 Workshop on Event-based Vision.
19.05.25: [New] Invited Talk at ICL on "4D Vision: From Sparse to Dense Reconstruction and Related Problems" (hosted by T. Birdal).
12.05.25: [New] Invited Tutorial on "Virtual Humans and Quantum-enhanced Computer Vision" at Eurographics 2025.
20.03.2025: Guest lecture at Princeton University: "Advanced Concepts in Neural Rendering and Reconstruction" (by Thomas Leimkuehler and myself).
02.01.2025: Invited Speaker at the ELIAS-ELLIS-VISMAC Winter School 2025 on Computer Vision, Pattern Recognition and Machine Learning.
02.12.2024: Invited Talk at the Australian Institute for Machine Learning (AIML; hosted by T.-J. Chin and S. Lucey).
25.11.2024: V. Rudnev received Outstanding Reviewer award at ECCV 2024.
07.10.2024: Invited Talk "3D Reconstruction and Generative Modelling of Non-rigid Scenes at the 4DQV Research Group" at Politecnico Milano (hosted by L. Magri and F. Aggironi).
25.09.2024: One paper accepted at NeurIPS 2024:
10.09.2024: Invited Tutorial at GCPR 2024 on Virtual Humans and Quantum-enhanced Computer Vision (QeCV) by M. Habermann and myself. The slides on Quantum-enhanced Computer Vision can be accessed here.
04.09.2024: Invited lecture on Quantum-Enhanced Computer Vision at the 3rd European Summer School on Quantum AI (EQAI 2024).
17.06.2024: Keynote speaker at the Physics Based Vision meets Deep Learning (PBDL) Workshop at CVPR 2024.
31.05.2024: Invited talk at 3D Vision Summer School (3DVSS) 2024.
15.04.2024: We are co-organising two workshops at ECCV 2024. More details coming soon!
  • TradiCV: 2nd Workshop on Traditional CV in the Age of Deep Learning
  • Quantum Computer Vision and Machine Learning (QCVML) Workshop (2nd Edition)
25.03.2024: We contributed two state-of-the-art reports at EUROGRAPHICS'24:
08.03.2024: We released UnrealEgo Benchmark for stereo egocentric 3D human pose estimation!
01.03.2024: Papers accepted at CVPR 2024:
16.10.2023: Papers accepted at 3DV 2024:
15.09.2023: 4DQV/VCAI contributed two journal and one conference proceedings papers to SIGGRAPH Asia 2023:
25.08.2023: We are organising a seminar on Quantum Computer Vision and Machine Learning (QCVML) (3CP) in WiSe 23/24.
18.08.2023: We are organising a lecture on Advanced Topics in Neural Rendering and 3D Reconstruction (3CP) in WiSe 23/24.
03.03.2023: Five papers at CVPR 2023 in Vancouver. Many thanks to all students, interns and collaborators!
31.01.2023: We will organise the CVMLCG Seminar 2023.
21.01.2023: A paper on quantum annealing with machine learning is accepted at ICLR 2023 as Spotlight.
22.12.2022: A state of the art report (STAR) conditionally accepted at EUROGRAPHICS 2023.
16.12.2022: We are going to organise a Workshop on Quantum Computer Vision and Machine Learning at CVPR 2023; in collaboration with Tongyang Li, Jan-Nico Zaech, Martin Danelljan, Jacob Biamonte and Tolga Birdal. More details coming soon.
13.12.2022: Two articles conditionally accepted at EUROGRAPHICS 2023.
08.12.2022: V. Golyanik gave a talk titled Advances in Quantum Computer Vision at the Workshop on Quantum Information at Saarland University (event poster). The slides can be found here. Many thanks to the organisers for making such an event happen!
21.10.2022: An article on random number generation on quantum annealers accepted at IEEE Access.
05.10.2022: The source code of MoCapDeform is now available here: GitHub link.
30.09.2022: A paper on high-fidelity 3D human performance capture accepted at BMVC 2022.
12.09.2022: MoCapDeform received Best Student Paper Award at 3DV 2022.
05.08.2022: A paper on global 3D human motion capture (MoCapDeform) accepted at 3DV 2022.
25.07.2022: 4DQV will present several papers at ECCV 2022:
04.07.2022: The source code of Physical Inertial Poser (PIP) is now available here: GitHub link.
27.06.2022: The source code of φ-SfT ist now available here: GitHub link.
21.04.2022: The source code of Neural PhysCap is now available via GitHub.
19.02.2022: We are co-organising a tutorial associated with our STAR on Advances in Neural Rendering on the 27th of April at EUROGRAPHICS'22.
28.03.2022: 4DQV will present three papers at CVPR 2022:
11.02.2022: State of the art report on neural rendering (the updated version) accepted at EUROGRAPHICS'22.
25.10.2021: The source code of Convex Joint Graph Matching and Clustering via Semidefinite Relaxations is released.
18.10.2021: An article is accepted at TPAMI (HandVoxNet++).
17.10.2021: Two papers accepted at 3DV 2021 (about graph matching and clustering and human image generation).
13.10.2021: EventHands is mentioned in ICCV 2021 Daily.
12.10.2021: The source code of GraviCap is released on GitHub
11.10.2021: The source code of Q-Match is released on GitHub.
27.09.2021: The source code of EventHands is released on GitHub.
08.09.2021: Dennis Willsch gave a 4DQV Lecture Series talk titled Applications on Quantum Annealers at Jülich Supercomputing Centre. The video can be found here.
19.08.2021: We are going to present the following works at ICCV 2021: GraviCap, Non-Rigid Neural Radiance Fields, Iterative Shape Matching via Quantum Annealing and EventHands.
05.07.2021: The source code of PhysCap is now available here.

Welcome to the web page of the 4D and Quantum Vision (4DQV) group led by Dr. Vladislav Golyanik. Our primary principles are 1) quality first in pursuit of scientific innovation and 2) maintaining an inclusive and collaborative environment.

Our world is inherently non-rigid at different spatial and temporal scales. Reconstructing it in 4D (3D+time) from visual observations remains challenging and has many practical applications. The challenges concern ill-posedness of the observations (e.g., monocular, which is of special interest) and scene conditions (e.g., partial observations, low light or high-speed motions), among others. To address those, 4DQV develops innovative approaches using RGB and event cameras for novel-view synthesis of deformable objects, humans and scenes; dense 3D deformation capture; sparse 3D pose estimation (hands and bodies); and generative 3D and video techniques. Furthermore, as a long-term goal, we investigate the advantages of quantum computational paradigms in solving combinatorial optimisation problems or providing alternatives to parameter-heavy neural networks in vision (e.g., in 3D scene representations learning, model fitting and mesh alignment aimed towards 4D reconstruction).

Our reserach interests include:

Publications

2025

2024

2023

2022

2021

The 4DQV Team

Co-Supervision

Master's Thesis Students

Alumni

Workshops

Teaching

Recent Talks

Source Codes


Datasets

See more details here.

Dr. Vladislav Golyanik [personal page] [e-mail]

4D and Quantum Computer Vision Group

Visual Computing and Artificial Intelligence Department