Abstract
Category-level object pose estimation (COPE), capable of generalizing to intra-class unknown objects, has become a core technique for robotic 3D scene understanding. However, existing COPE methods still require labor-intensive recollection of real-world training data for novel object categories, which limits their scalability in practical applications. This paper aims to achieve synthetic-to-real (Syn2Real) generalized COPE, where a model is trained solely on rendered synthetic data and directly generalized to real-world deployments. The central challenge lies in the significant domain gap between synthetic and real-world data, particularly in texture appearance. To address this, we aim to enhance domain generalization by learning domain-invariant representations that capture semantic commonalities among objects within the same category. We introduce 2D and 3D semantic consistency constraints to reduce the sensitivity of feature encoders to domain-specific features. In addition, we propose an end-to-end pose regression framework that performs 2D-3D cross consistency learning, leveraging dense cross-modality fusion to further refine pose estimation. Since simplicity and effectiveness are essential for real-world robotic deployment, our model operates exclusively on global features, yielding a highly lightweight and efficient architecture. Extensive experiments on the REAL275 and Wild6D benchmarks, as well as real-world robotic manipulation scenes, show superior Syn2Real generalization performance of our paradigm. Code and demos are released at https://paperreview99.github.io/GenCOPE/.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liu, J., Sun, W., Dai, Z., Yang, H., Xiao, J., Sebe, N., & Zhao, N. (2026). GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking. https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking
MLA 9
Liu, Jian, et al. "GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking." https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking.
Chicago (author–date)
Liu, Jian, Wei Sun, Zhenqi Dai, Hui Yang, Jian Xiao, Nicu Sebe, and Na Zhao. 2026. "GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking." https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking.
Harvard
Liu, J., Sun, W., Dai, Z., Yang, H., Xiao, J., Sebe, N. and Zhao, N. (2026) 'GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking', Available at: https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking.
Vancouver
Liu J, Sun W, Dai Z, Yang H, Xiao J, Sebe N, et al. GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking. https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking
IEEE
J. Liu, W. Sun, Z. Dai, H. Yang, J. Xiao, N. Sebe, and N. Zhao, "GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking," https://omanscience.com/en/articles/gencope-syn2real-generalized-category-level-object-pose-estimation-for-robotic-picking.