Zunnan Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zunnan Xu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Xiu Li
Tsinghua University
3 shared publications - Haonan Han
Tsinghua University, Shenzhen, Guangdong, China
2 shared publications - Jiaqi Huang
Shenzhen International Graduate School, Tsinghua University,Shenzhen,China
2 shared publications - Mingwen Ou
Shenzhen International Graduate School, Tsinghua University,Shenzhen,China
2 shared publications - Ronghui Li
Tsinghua University, Shenzhen, China
2 shared publications - Ting Liu
Hunan Police College, China
2 shared publications
Latest Publications
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 993-998
TGS-LGP: Text-Guided Medical Image Segmentation Via Local-Global Perception
In this paper, we propose TGS-LGP, a framework for text-guided medical image segmentation that synergistically combines cross-modal understanding with local-global features perception. Our method employs a local-global text encoder that simultaneously processes clinical language inputs through two complementary pathways: one leverages contrastive language-image pretraining to capture global semantic context, and another employes domain-specific linguistic analysis to extract fine-grained lesion characteristics. These multiscale textual representations are progressively fused with refined visual features through an attention-based decoder that dynamically fuse cross-modal features. This architectural design enables context-aware integration of diagnostic text guidance with radiological image patterns. Additionally, we introduce vision refiner, a novel component that effectively integrates global features of medical images with minimal computational cost, compensating for the information loss caused by the local modeling bias of CNNs in medical imaging. This enhancement strengthens visual representation, thereby facilitating more effective fusion with textual features. Experimental results on two widely used benchmarks demonstrate that our method achieves the best accuracy compared to state-of-the-art methods.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 993-998
TGS-LGP: Text-Guided Medical Image Segmentation Via Local-Global Perception
In this paper, we propose TGS-LGP, a framework for text-guided medical image segmentation that synergistically combines cross-modal understanding with local-global features perception. Our method employs a local-global text encoder that simultaneously processes clinical language inputs through two complementary pathways: one leverages contrastive language-image pretraining to capture global semantic context, and another employes domain-specific linguistic analysis to extract fine-grained lesion characteristics. These multiscale textual representations are progressively fused with refined visual features through an attention-based decoder that dynamically fuse cross-modal features. This architectural design enables context-aware integration of diagnostic text guidance with radiological image patterns. Additionally, we introduce vision refiner, a novel component that effectively integrates global features of medical images with minimal computational cost, compensating for the information loss caused by the local modeling bias of CNNs in medical imaging. This enhancement strengthens visual representation, thereby facilitating more effective fusion with textual features. Experimental results on two widely used benchmarks demonstrate that our method achieves the best accuracy compared to state-of-the-art methods.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10305-10314
InterAnimate: Taming Region-Aware Diffusion Model for Realistic Human Interaction Animation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10305-10314
Open AccessInterAnimate: Taming Region-Aware Diffusion Model for Realistic Human Interaction Animation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9743-9752
Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9743-9752
Open AccessSeparate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6715-6724
Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
Reconstructing 3D objects from a single image guided by pretrained diffusion models has demonstrated promising outcomes. However, due to utilizing the case-agnostic rigid strategy, their generalization ability to arbitrary cases and the 3D consistency of reconstruction are still poor. In this work, we propose Consistent123, a case-aware two-stage method for highly consistent 3D asset reconstruction from one image with both 2D and 3D diffusion priors. In the first stage, Consistent123 utilizes only 3D structural priors for sufficient geometry exploitation, with a CLIP-based case-aware adaptive detection mechanism embedded within this process. In the second stage, 2D texture priors are introduced and progressively take on a dominant guiding role, delicately sculpting the details of the 3D model. Consistent123 aligns more closely with the evolving trends in guidance requirements, adaptively providing adequate 3D geometric initialization and suitable 2D texture refinement for different objects. Consistent123 can obtain highly 3D-consistent reconstruction and exhibits strong generalization ability across various objects. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art image-to-3D methods.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6715-6724
Open AccessConsistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
Reconstructing 3D objects from a single image guided by pretrained diffusion models has demonstrated promising outcomes. However, due to utilizing the case-agnostic rigid strategy, their generalization ability to arbitrary cases and the 3D consistency of reconstruction are still poor. In this work, we propose Consistent123, a case-aware two-stage method for highly consistent 3D asset reconstruction from one image with both 2D and 3D diffusion priors. In the first stage, Consistent123 utilizes only 3D structural priors for sufficient geometry exploitation, with a CLIP-based case-aware adaptive detection mechanism embedded within this process. In the second stage, 2D texture priors are introduced and progressively take on a dominant guiding role, delicately sculpting the details of the 3D model. Consistent123 aligns more closely with the evolving trends in guidance requirements, adaptively providing adequate 3D geometric initialization and suitable 2D texture refinement for different objects. Consistent123 can obtain highly 3D-consistent reconstruction and exhibits strong generalization ability across various objects. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art image-to-3D methods.