Quantum Motion Segmentation

Arrigoni, Federica; Menapace, Willi; Seelbach, Benkner, Marcel; Ricci, Elisa; Golyanik, Vladislav

doi:10.1007/978-3-031-19818-2_29

Cited by 6 publications

(4 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several quantum techniques are available for computer vision tasks, such as recognition and classification [19,20], object tracking [21], transformation estimation [22], shape alignment and matching [23][24][25], permutation synchronization [26], visual clustering [27], and motion segmentation [28]. Via Adiabatic Quantum Computing (AQC), O'Malley et al [19] applied binary matrix factorization to extract features of facial images.…”

Section: Quantum Computer Visionmentioning

confidence: 99%

See 1 more Smart Citation

Quantum Visual Feature Encoding Revisited

Nguyen,

Churchill

et al. 2024

Preprint

View full text Add to dashboard Cite

Although quantum machine learning has been introduced for a while, its applications in computer vision are still limited. This paper, therefore, revisits the quantum visual encoding strategies, the initial step in quantum machine learning. Investigating the root cause, we uncover that the existing quantum encoding design fails to ensure information preservation of the visual features after the encoding process, thus complicating the learning process of the quantum machine learning models. In particular, the problem, termed ”Quantum Information Gap” (QIG), leads to a gap of information between classical and corresponding quantum features. We provide theoretical proof and practical examples with visualization for that found and underscore the significance of QIG, as it directly impacts the performance of quantum machine learning algorithms. To tackle this challenge, we introduce a simple but efficient new loss function named Quantum Information Preserving (QIP) to minimize this gap, resulting in enhanced performance of quantum machine learning algorithms. Extensive experiments validate the effectiveness of our approach, showcasing superior performance compared to current methodologies and consistently achieving state-of-the-art results in quantum modeling.

show abstract

Section: Quantum Computer Visionmentioning

confidence: 99%

“…Using AQC to solve the formulated Quadratic Unconstrained Binary Optimization (QUBO), Nguyen et al [27] proposed an unsupervised visual clustering method optimizing the distances between clusters. In contrast, Arrigoni et al [28] optimized the matching motions of key points between consecutive frames.…”

Section: Quantum Computer Visionmentioning

confidence: 99%

Quantum Visual Feature Encoding Revisited

Nguyen,

Churchill

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Quantum Computer Vision (QCV). Several algorithms for computer vision relying on quantum hardware were proposed over the last three years for such problems as shape matching [23,35,42], object tracking [32,47], fundamental matrix estimation, point triangulation [20] and motion segmentation [1], among others. The majority of them address various types of alignment problems, i.e., transformation estimation [23,35], point set [23,37] and mesh alignment [42], graph matching [3,41] and permutation synchronisation [3].…”

Section: Related Workmentioning

confidence: 99%

“…As QPU time is expensive and since we have just shown that SA performs comparably to a QPU in terms of result quality, we perform the remaining experiments with SA under our default settings, on classical hardware. This is common practice [1,42,47] since SA is conceptually close to QA. For additional results, including results on the new Zephyr hardware [14], we refer to the supplement.…”

Section: Experiments On Real Quantum Annealermentioning

confidence: 99%

CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Bhatia¹,

Tretschk²,

Lähner³

et al. 2023

Preprint

View full text Add to dashboard Cite

Jointly matching multiple, non-rigidly deformed 3D shapes is a challenging, N P-hard problem. A perfect matching is necessarily cycle-consistent: Following the pairwise point correspondences along several shapes must end up at the starting vertex of the original shape. Unfortunately, existing quantum shape-matching methods do not support multiple shapes and even less cycle consistency. This paper addresses the open challenges and introduces the first quantum-hybrid approach for 3D shape multimatching; in addition, it is also cycle-consistent. Its iterative formulation is admissible to modern adiabatic quantum hardware and scales linearly with the total number of input shapes. Both these characteristics are achieved by reducing the N -shape case to a sequence of three-shape matchings, the derivation of which is our main technical contribution. Thanks to quantum annealing, high-quality solutions with low energy are retrieved for the intermediate N Phard objectives. On benchmark datasets, the proposed approach significantly outperforms extensions to multi-shape matching of a previous quantum-hybrid two-shape matching method and is on-par with classical multi-matching methods. Our source code is available at 4dqv.mpiinf.mpg.de/CCuantuMM/.

show abstract

Quantum Computing for Computer Vision: Applications, Challenges, and Research Tracks

Mebtouche,

Sahnoune

2024

Information Systems Engineering and Management

View full text Add to dashboard Cite

Quantum Motion Segmentation

Cited by 6 publications

References 51 publications

Quantum Visual Feature Encoding Revisited

Quantum Visual Feature Encoding Revisited

CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Quantum Computing for Computer Vision: Applications, Challenges, and Research Tracks

Contact Info

Product

Resources

About