الملخص
Category-level 6D pose estimation from a single RGB-D observation is inherently under-constrained, since partial visible geometry must be interpreted together with a canonical object structure before a stable pose can be determined. We present LEGAU, a unified framework that jointly predicts NOCS correspondence, object pose and size, and a canonical Semantic Gaussian Field. Rather than treating reconstruction as a detached auxiliary task, LEGAU uses the Gaussian field as a category-conditioned structural prior that participates in multimodal feature fusion and provides global guidance for local pose reasoning. Conditioned on a categorical text embedding, LEGAU processes RGB-D observations through a transformer-based fusion module that integrates visual, geometric, and category-level cues, decoding the NOCS map, pose and size information and the Gaussian-based object representation. Extensive experiments on synthetic and real-world benchmarks show that this coupled pose-shape formulation achieves strong performance in a single-model multi-category setting, with up to 22\% on SOPE and competitive transfer to real-world data. These results highlight the benefit of jointly learning canonical correspondence, object shape, and pose alignment within a unified representation.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xu, H., Lu, Z., Huang, J., Hu, J., Yu, P. K., Busam, B., Tombari, F., & ilic, S. (2026). LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation. https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation
MLA 9
Xu, Hongli, et al. "LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation." https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation.
شيكاغو (المؤلف–التاريخ)
Xu, Hongli, Zhaowei Lu, Junwen Huang, Jiaqi Hu, Peter KT Yu, Benjamin Busam, Federico Tombari, and Slobodan ilic. 2026. "LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation." https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation.
هارفارد
Xu, H., Lu, Z., Huang, J., Hu, J., Yu, P. K., Busam, B., Tombari, F. and ilic, S. (2026) 'LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation', Available at: https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation.
فانكوفر
Xu H, Lu Z, Huang J, Hu J, Yu PK, Busam B, et al. LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation. https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation
IEEE
H. Xu, Z. Lu, J. Huang, J. Hu, P. K. Yu, B. Busam, F. Tombari, and S. ilic, "LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation," https://omanscience.com/ar/articles/legau-learning-semantic-gaussian-priors-for-scalable-category-level-pose-estimation.