EUVIMEDEUVIMED entdecken
Crossref

Toward Accurate Human Parsing Through Edge Guided Diffusion

Ting Liu, Hongkun Zhu, Yunchao Wei, Shikui Wei, Yao Zhao, Yanning Zhang

IEEE Transactions on Image Processing · 2024 · 33 · 2530-2543

DOI: 10.1109/tip.2024.3379931 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Ting Liu und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Benchmarking, Learning. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing human parsing frameworks commonly employ joint learning of semantic edge detection and human parsing to facilitate the localization around boundary regions. Nevertheless, the parsing prediction within the interior of the part contour may still exhibit inconsistencies due to the inherent ambiguity of fine-grained semantics. In contrast, binary edge detection does not suffer from such fine-grained semantic ambiguity, leading to a typical failure case where misclassification occurs inner the part contour while the semantic edge is accurately detected. To address these challenges, we develop a novel diffusion scheme that incorporates guidance from the detected semantic edge to mitigate this problem by propagating corrected classified semantics into the misclassified regions. Building upon this diffusion scheme, we present an Edge Guided Diffusion Network (EGDNet) for human parsing, which can progressively refine the parsing predictions to enhance the accuracy and coherence of human parsing results. Moreover, we design a horizontal-vertical aggregation to exploit inherent correlations among body parts along both the horizontal and vertical axes, which aims at enhancing the initial parsing results. Extensive experimental evaluations on various challenging datasets demonstrate the effectiveness of the proposed EGDNet. Remarkably, our EGDNet shows impressive performances on six benchmark datasets, including four human body parsing datasets (LIP, CIHP, ATR, and PASCAL-Person-Part), and two human face parsing datasets (CelebAMask-HQ and LaPa).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BenchmarkingLearningHumansSemantics

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • China Postdoctoral Science Foundation

Zitieren

APA

Liu, T., Zhu, H., Wei, Y., Wei, S., Zhao, Y., & Zhang, Y. (2024). Toward Accurate Human Parsing Through Edge Guided Diffusion. IEEE Transactions on Image Processing, 33, 2530-2543. https://doi.org/10.1109/tip.2024.3379931

Vancouver

Liu T, Zhu H, Wei Y, Wei S, Zhao Y, Zhang Y. Toward Accurate Human Parsing Through Edge Guided Diffusion. IEEE Transactions on Image Processing. 2024;33:2530-2543. doi:10.1109/tip.2024.3379931

BibTeX
@article{Liu2024,
  author = {Liu, Ting and Zhu, Hongkun and Wei, Yunchao and Wei, Shikui and Zhao, Yao and Zhang, Yanning},
  title = {Toward Accurate Human Parsing Through Edge Guided Diffusion},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {2530--2543},
  doi = {10.1109/tip.2024.3379931}
}
Kostenlos starten →