Academic Journal

One-Stage Absolute Human Mesh Recovery.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: One-Stage Absolute Human Mesh Recovery.
Συγγραφείς: Liao X, Su W, Zhang C, Li X, Tao W
Πηγή: IEEE transactions on visualization and computer graphics [IEEE Trans Vis Comput Graph] 2026 Jul; Vol. 32 (7), pp. 5198-5209.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: IEEE Computer Society Country of Publication: United States NLM ID: 9891704 Publication Model: Print Cited Medium: Internet ISSN: 1941-0506 (Electronic) Linking ISSN: 10772626 NLM ISO Abbreviation: IEEE Trans Vis Comput Graph Subsets: MEDLINE
Imprint Name(s): Original Publication: New York, NY : IEEE Computer Society, c1995-
Ιατρικοί όροι (MeSH): Imaging, Three-Dimensional*/methods , Computer Graphics*, Algorithms ; Humans
Περίληψη: The reconstruction of realistic and precise human meshes in world coordinates is facilitated by considering scene information. Challenges related to accuracy, robustness, and computation time are faced by existing absolute human mesh recovery methods. In this paper, a one-stage model for absolute human mesh recovery with superior reconstruction precision and inference speed is presented. The proposed one-stage model is composed of two parallel branches to achieve root position estimation and human mesh regression. To effectively connect the two branches, a scene-image information aggregation module is designed. The accuracy of the estimated human meshes is improved and the end-to-end training of the whole model is facilitated by this module. Experiments are conducted on three diverse datasets, and a GMPJPE decrease of 72.3 mm/27.32% and an MPJPE reduction of 25.6 mm/27.26% are achieved by the proposed method with the lowest inference time compared to previous SOTA methods.
Entry Date(s): Date Created: 20260212 Date Completed: 20260722 Latest Revision: 20260722
Update Code: 20260723
DOI: 10.1109/TVCG.2026.3664111
PMID: 41678487
Βάση Δεδομένων: MEDLINE