EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust human pose generation via uncertainty aware structural reward modeling

Deliang Zhang, Songyin Dai, Bingxin Xu, Hongzhe Liu, Weiguo Pan, Cheng Xu

Discover Artificial Intelligence · 02.06.2026 · 6 (1)

DOI: 10.1007/s44163-026-01487-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Discover Artificial Intelligence, online erschienen am 02.06.2026. Verfasst von Deliang Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conditional diffusion models offer a versatile paradigm for controllable image synthesis, yet faithfully adhering to intricate spatial constraints, such as human pose skeletons, continues to pose significant challenges. Despite progress in control architectures and reward-guided fine-tuning, outputs frequently exhibit structural aberrations, joint misalignments, and anatomically infeasible configurations. We contend that these shortcomings arise primarily from two core deficiencies: pixel-based rewards inadequately encapsulate the perceptual and topological nuances of skeletal forms, and reward signals grow unreliable amid diverse or out-of-distribution samples. To address this, we introduce Dream Your Pose , a perceptually informed framework for pose-conditioned generation that prioritizes structural fidelity. Our method incorporates a multi-channel, structure-sensitive reward mechanism, harnessing perceptual features like local contrast, edge gradients, and spatial continuity to more accurately gauge pose congruence. Critically, we integrate an uncertainty-aware regularization paradigm—drawing from principles of uncertainty modeling in learning—to adaptively modulate reward influence, thereby mitigating the effects of spurious or ambiguous feedback and fostering robust training dynamics. Rigorous evaluations on the OpenPose-ControlNet dataset reveal substantial gains, compared with the retrained ControlNet baseline, including a 25.3% relative uplift in Object Keypoint Similarity (OKS) and a 15.6% enhancement in Probability of Correct Keypoint at 0.5 (PCK@0.5), underscoring improved keypoint precision and holistic skeletal integrity. These advancements yield images with superior visual coherence and anatomical plausibility, without compromising semantic fidelity or perceptual quality.

Zitieren

APA

Zhang, D., Dai, S., Xu, B., Liu, H., Pan, W., & Xu, C. (2026). Robust human pose generation via uncertainty aware structural reward modeling. Discover Artificial Intelligence, 6(1). https://doi.org/10.1007/s44163-026-01487-7

Vancouver

Zhang D, Dai S, Xu B, Liu H, Pan W, Xu C. Robust human pose generation via uncertainty aware structural reward modeling. Discover Artificial Intelligence. 2026;6(1). doi:10.1007/s44163-026-01487-7

BibTeX
@article{Zhang2026,
  author = {Zhang, Deliang and Dai, Songyin and Xu, Bingxin and Liu, Hongzhe and Pan, Weiguo and Xu, Cheng},
  title = {Robust human pose generation via uncertainty aware structural reward modeling},
  journal = {Discover Artificial Intelligence},
  year = {2026},
  volume = {6},
  number = {1},
  doi = {10.1007/s44163-026-01487-7}
}
Kostenlos starten →