Yangbin Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yangbin Xu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Jian Liu
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
4 shared publications - Jiangang Yang
Chinese Academy of Sciences
3 shared publications - Luqing Luo
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
2 shared publications - Wenhui Shi
Institute of Microelectronics, Chinese Academy of Sciences, No. 3 Beitucheng West Road, Chaoyang District, Beijing, 100029, Beijing, China; University of Chinese Academy of Science, Beijing, 100049, Beijing, China
2 shared publications - Haiyang Liu
Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China
1 shared publication Jian Liu
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, People’s Republic of China
1 shared publication
Latest Publications
- Open Access
- 12 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (7) , 425
KNA-SG: Keyframe–Node-Associated Open-Vocabulary 3D Scene Graphs from RGB Sequences
3D scene graphs organize objects and their relationships in a scene into structured representations, providing an interpretable and queryable foundation for relational reasoning and object grounding. Existing open-vocabulary 3D scene graph construction methods primarily focus on object-level feature representation and open-ended edge reasoning. However, they often lack explicit and retrievable associations between object nodes and keyframes, making it difficult to recall relevant visual evidence for target disambiguation and relationship verification in complex queries. Moreover, pre-constructed edges are inherently limited in their ability to cover the diverse linguistic expressions encountered in downstream tasks. To address these limitations, we propose KNA-SG, a framework for constructing open-vocabulary 3D scene graphs from RGB sequences with explicit keyframe–node associations. Built upon instance-grounded 3D reconstruction, KNA-SG represents each object instance as a graph node and uses a unique instance identifier to associate the node with the keyframes in which the instance is observed. The ID-annotated keyframes guide MLLM-based open-vocabulary semantic parsing, enabling semantic attributes to be assigned to these graph nodes. This design transforms keyframes into retrievable visual evidence for target disambiguation and relationship verification during query reasoning. Verified relationships are further written back into the scene graph as reusable relational memory to support subsequent queries. To ensure the effectiveness of selected keyframes, we design a two-stage keyframe selection strategy that combines visual quality assessment with semantic redundancy removal, preserving a set of clear keyframes that provide comprehensive scene coverage. Experimental results show that KNA-SG outperforms existing methods on open-vocabulary 3D semantic segmentation and 3D object grounding tasks.
- 12 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (7) , 425
Open AccessKNA-SG: Keyframe–Node-Associated Open-Vocabulary 3D Scene Graphs from RGB Sequences
3D scene graphs organize objects and their relationships in a scene into structured representations, providing an interpretable and queryable foundation for relational reasoning and object grounding. Existing open-vocabulary 3D scene graph construction methods primarily focus on object-level feature representation and open-ended edge reasoning. However, they often lack explicit and retrievable associations between object nodes and keyframes, making it difficult to recall relevant visual evidence for target disambiguation and relationship verification in complex queries. Moreover, pre-constructed edges are inherently limited in their ability to cover the diverse linguistic expressions encountered in downstream tasks. To address these limitations, we propose KNA-SG, a framework for constructing open-vocabulary 3D scene graphs from RGB sequences with explicit keyframe–node associations. Built upon instance-grounded 3D reconstruction, KNA-SG represents each object instance as a graph node and uses a unique instance identifier to associate the node with the keyframes in which the instance is observed. The ID-annotated keyframes guide MLLM-based open-vocabulary semantic parsing, enabling semantic attributes to be assigned to these graph nodes. This design transforms keyframes into retrievable visual evidence for target disambiguation and relationship verification during query reasoning. Verified relationships are further written back into the scene graph as reusable relational memory to support subsequent queries. To ensure the effectiveness of selected keyframes, we design a two-stage keyframe selection strategy that combines visual quality assessment with semantic redundancy removal, preserving a set of clear keyframes that provide comprehensive scene coverage. Experimental results show that KNA-SG outperforms existing methods on open-vocabulary 3D semantic segmentation and 3D object grounding tasks.
- 19 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109152
Robust network pruning for enhanced accuracy under perturbations via structural and distributional consistency
- 19 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109152
Robust network pruning for enhanced accuracy under perturbations via structural and distributional consistency
- 5 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 340
Preserving information flow stability for robust network pruning
- 5 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 340
Preserving information flow stability for robust network pruning
- 24 June 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (7) , 076303
Category-level object pose estimation via novel feature fusion and two-stage pose regression
Category-level object pose estimation has attracted attention in robotics and augmented reality, as it enables generalization to unseen instances within known categories. However, significant intra-category shape variations and the complexity of effectively integrating geometric and visual information pose challenges to accurate pose and size estimation in vision measurement. Leveraging the widespread availability of affordable RGB-D sensors, this study explores an effective strategy for extracting and fusing appearance and geometric features to improve estimation performance. We introduce a vision foundation model for robust appearance feature extraction and propose a novel point-to-patch feature fusion strategy that leverages pixel-wise RGB-D correspondence to concatenate patch-level appearance features with point-level geometric features. The estimation process follows a two-stage paradigm, where object translation and size are first predicted, followed by rotation estimation guided by an auxiliary branch designed to facilitate learning of rotation-aware transformations. The proposed method achieves state-of-the-art performance on the CAMERA25 and REAL275 datasets, with enhanced generalization on the Wild6D dataset. Additionally, it supports real-time inference at 34 FPS on a single NVIDIA RTX A6000 GPU.
- 24 June 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (7) , 076303
Category-level object pose estimation via novel feature fusion and two-stage pose regression
Category-level object pose estimation has attracted attention in robotics and augmented reality, as it enables generalization to unseen instances within known categories. However, significant intra-category shape variations and the complexity of effectively integrating geometric and visual information pose challenges to accurate pose and size estimation in vision measurement. Leveraging the widespread availability of affordable RGB-D sensors, this study explores an effective strategy for extracting and fusing appearance and geometric features to improve estimation performance. We introduce a vision foundation model for robust appearance feature extraction and propose a novel point-to-patch feature fusion strategy that leverages pixel-wise RGB-D correspondence to concatenate patch-level appearance features with point-level geometric features. The estimation process follows a two-stage paradigm, where object translation and size are first predicted, followed by rotation estimation guided by an auxiliary branch designed to facilitate learning of rotation-aware transformations. The proposed method achieves state-of-the-art performance on the CAMERA25 and REAL275 datasets, with enhanced generalization on the Wild6D dataset. Additionally, it supports real-time inference at 34 FPS on a single NVIDIA RTX A6000 GPU.
- Open Access
Regularized Denoising Masked Visual Pretraining for Robust Embodied PointGoal Navigation
Embodied PointGoal navigation is a fundamental task for embodied agents. Recent works have shown that the performance of the embodied navigation agent degrades significantly in the presence of visual corruption, including Spatter, Speckle Noise, and Defocus Blur, showing the weak robustness of the agent. To improve the robustness of embodied navigation agents to various visual corruptions, we propose a navigation framework called Regularized Denoising Masked AutoEncoders Navigation (RDMAE-Nav). In a nutshell, RDMAE-Nav mainly consists of two modules: a visual module and a policy module. In the visual module, a self-supervised pretraining method, dubbed Regularized Denoising Masked AutoEncoders (RDMAE), is designed to enable the Vision Transformers (ViT)-based visual encoder to learn robust representations. The bidirectional Kullback–Leibler divergence is introduced in RDMAE as the regularization term for a denoising masked modeling task. Specifically, RDMAE mitigates the gap between clean and noisy image representations by minimizing the bidirectional Kullback–Leibler divergence. Then, the visual encoder is pretrained by RDMAE. In contrast to existing works, RDMAE-Nav applies denoising masked visual pretraining for PointGoal navigation to improve robustness to various visual corruptions. Finally, the pretrained visual encoder with frozen weights is applied to extract robust visual representations for policy learning in the RDMAE-Nav. Extensive experiments show that RDMAE-Nav performs competitively compared with state of the arts (SOTAs) on various visual corruptions. In detail, RDMAE-Nav performs the absolute improvement: 28.2% in SR and 23.68% in SPL under Spatter; 2.28% in SR and 6.41% in SPL under Speckle Noise; and 9.46% in SR and 9.55% in SPL under Defocus Blur.
Open AccessRegularized Denoising Masked Visual Pretraining for Robust Embodied PointGoal Navigation
Embodied PointGoal navigation is a fundamental task for embodied agents. Recent works have shown that the performance of the embodied navigation agent degrades significantly in the presence of visual corruption, including Spatter, Speckle Noise, and Defocus Blur, showing the weak robustness of the agent. To improve the robustness of embodied navigation agents to various visual corruptions, we propose a navigation framework called Regularized Denoising Masked AutoEncoders Navigation (RDMAE-Nav). In a nutshell, RDMAE-Nav mainly consists of two modules: a visual module and a policy module. In the visual module, a self-supervised pretraining method, dubbed Regularized Denoising Masked AutoEncoders (RDMAE), is designed to enable the Vision Transformers (ViT)-based visual encoder to learn robust representations. The bidirectional Kullback–Leibler divergence is introduced in RDMAE as the regularization term for a denoising masked modeling task. Specifically, RDMAE mitigates the gap between clean and noisy image representations by minimizing the bidirectional Kullback–Leibler divergence. Then, the visual encoder is pretrained by RDMAE. In contrast to existing works, RDMAE-Nav applies denoising masked visual pretraining for PointGoal navigation to improve robustness to various visual corruptions. Finally, the pretrained visual encoder with frozen weights is applied to extract robust visual representations for policy learning in the RDMAE-Nav. Extensive experiments show that RDMAE-Nav performs competitively compared with state of the arts (SOTAs) on various visual corruptions. In detail, RDMAE-Nav performs the absolute improvement: 28.2% in SR and 23.68% in SPL under Spatter; 2.28% in SR and 6.41% in SPL under Speckle Noise; and 9.46% in SR and 9.55% in SPL under Defocus Blur.