ProM-Pose: Language-Guided Zero-Shot 9-DoF Object Pose Estimation from RGB-D with Generative 3D Priors
Electronics · 2026-03-07 · 15 (5) · 1111
DOI: 10.3390/electronics15051111 ↗At a glance
Journal article in Electronics, published online on 2026-03-07. Written by Yuchen Li and 3 co-authors. Cited 1 times so far (Crossref); 73 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Key Research and Development Program of China.
Abstract (original language)
Object pose estimation is fundamental for robotic manipulation, autonomous driving, and augmented reality, yet recovering the full 9-DoF state (rotation, translation, and anisotropic 3D scale) from RGB-D observations remains challenging for previously unseen objects. Existing methods either rely on instance-specific CAD models, predefined category boundaries, or suffer from scale ambiguity under sparse observations. We propose ProM-Pose, a unified cross-modal temporal perception framework for zero-shot 9-DoF object pose estimation. By integrating language-conditioned generative 3D shape priors as canonical geometric references, an asymmetric cross-modal attention mechanism for spatially aware fusion, and a decoupled pose decoding strategy with temporal refinement, ProM-Pose constructs metrically consistent and semantically grounded representations without relying on category-specific pose priors or instance-level CAD supervision. Extensive experiments on CAMERA25 and REAL275 benchmarks demonstrate that ProM-Pose achieves competitive or superior performance compared to category-level methods, with mAP of 75.0% at 5°,2cm and 90.5% at 10°,5cm on CAMERA25, and 42.2% at 5°,2cm and 76.0% at 10°,5cm on REAL275 under zero-shot cross-domain evaluation. Qualitative results on real-world logistics scenarios further validate temporal stability and robustness under occlusion and lighting variations. ProM-Pose effectively bridges semantic grounding and metric geometric reasoning within a unified formulation, enabling stable and scale-aware 9-DoF pose estimation for previously unseen objects under open-vocabulary conditions.
Funding
- National Key Research and Development Program of China
Cite
APA
Li, Y., Qin, K., Wu, H., & Qu, X. (2026). ProM-Pose: Language-Guided Zero-Shot 9-DoF Object Pose Estimation from RGB-D with Generative 3D Priors. Electronics, 15(5), 1111. https://doi.org/10.3390/electronics15051111
Vancouver
Li Y, Qin K, Wu H, Qu X. ProM-Pose: Language-Guided Zero-Shot 9-DoF Object Pose Estimation from RGB-D with Generative 3D Priors. Electronics. 2026;15(5):1111. doi:10.3390/electronics15051111
BibTeX
@article{Li2026,
author = {Li, Yuchen and Qin, Kai and Wu, Haitao and Qu, Xiangjun},
title = {ProM-Pose: Language-Guided Zero-Shot 9-DoF Object Pose Estimation from RGB-D with Generative 3D Priors},
journal = {Electronics},
year = {2026},
volume = {15},
number = {5},
pages = {1111},
doi = {10.3390/electronics15051111}
}
EUVIMED