Copertina

POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search

Salvato in:
Pubblicato in:arXiv.org (Dec 20, 2024), p. n/a
Autore principale: Chong-Yang, Xiang
Altri autori: Jun-Yan, He, Zhi-Qi, Cheng, Wu, Xiao, Xian-Sheng Hua
Pubblicazione:
Cornell University Library, arXiv.org
Soggetti:
Accuracy
Parallel processing
Algorithms
Encoding-Decoding
Robustness (mathematics)
Software
Computing time
Accesso online:Citation/Abstract
Full text outside of ProQuest
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3117170463
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3117170463 
045 0 |b d20241220 
100 1 |a Chong-Yang, Xiang 
245 1 |a POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search 
260 |b Cornell University Library, arXiv.org  |c Dec 20, 2024 
513 |a Working Paper 
520 3 |a Achieving a balance between accuracy and efficiency is a critical challenge in facial landmark detection (FLD). This paper introduces Parallel Optimal Position Search (POPoS), a high-precision encoding-decoding framework designed to address the limitations of traditional FLD methods. POPoS employs three key contributions: (1) Pseudo-range multilateration is utilized to correct heatmap errors, improving landmark localization accuracy. By integrating multiple anchor points, it reduces the impact of individual heatmap inaccuracies, leading to robust overall positioning. (2) To enhance the pseudo-range accuracy of selected anchor points, a new loss function, named multilateration anchor loss, is proposed. This loss function enhances the accuracy of the distance map, mitigates the risk of local optima, and ensures optimal solutions. (3) A single-step parallel computation algorithm is introduced, boosting computational efficiency and reducing processing time. Extensive evaluations across five benchmark datasets demonstrate that POPoS consistently outperforms existing methods, particularly excelling in low-resolution heatmaps scenarios with minimal computational overhead. These advantages make POPoS a highly efficient and accurate tool for FLD, with broad applicability in real-world scenarios. 
653 |a Accuracy 
653 |a Parallel processing 
653 |a Algorithms 
653 |a Encoding-Decoding 
653 |a Robustness (mathematics) 
653 |a Software 
653 |a Computing time 
700 1 |a Jun-Yan, He 
700 1 |a Zhi-Qi, Cheng 
700 1 |a Wu, Xiao 
700 1 |a Xian-Sheng Hua 
773 0 |t arXiv.org  |g (Dec 20, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3117170463/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2410.09583