Ying Tai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ying Tai has a total of 153 co-authors. Here are the top co-authors by number of shared publications:
Jian Yang
Nanjing University
13 shared publications- Jun Li
Southeast University
12 shared publications - Jian Yang
Nanjing University of Science and Technology, Nanjing, China
9 shared publications - Chen Zhao
Nanjing University
5 shared publications - Chengjie Wang
YouTu Lab, Tencent, Shanghai, China
4 shared publications - Zhenyu Zhang
Nanjing University
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17870-17876
ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17870-17876
Open AccessArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (11) , 16289-16300
TCPort: Text-Guided Creative Portrait Animation
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (11) , 16289-16300
TCPort: Text-Guided Creative Portrait Animation
- 16 September 2026
- Published by Springer Nature
- p. 65-85
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
- 16 September 2026
- Published by Springer Nature
- p. 65-85
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
- 11 September 2026
- Published by Springer Nature
- p. 201-218
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model
- 11 September 2026
- Published by Springer Nature
- p. 201-218
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model
- Top Cited Papers
- 2 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (9) , 416
OpenVid++: A Large-scale High-quality Dataset for Text-to-video Generation
- 2 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (9) , 416
Top Cited PapersOpenVid++: A Large-scale High-quality Dataset for Text-to-video Generation
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 5144-5155
DreamBarbie: Text to Barbie-Style 3D Avatars
To integrate digital humans into everyday life, there is a strong demand for generating high-quality, fine-grained disentangled 3D avatars that support expressive animation and simulation capabilities, ideally from low-cost textual inputs. Although text-driven 3D avatar generation has made significant progress by leveraging 2D generative priors, existing methods still struggle to fulfill all these requirements simultaneously. To address this challenge, we propose DreamBarbie, a novel text-driven framework for generating animatable 3D avatars with separable shoes, accessories, and simulation-ready garments, truly capturing the iconic "Barbie doll" aesthetic. The core of our framework lies in an expressive 3D representation combined with appropriate modeling constraints. Unlike prior methods, we use G-Shell to uniformly model watertight components (e.g., bodies, shoes) and non-watertight garments. By reformulating boundaries as euclidean field intersections instead of manifold geodesics, we propose an SDF-based initialization and a hole regularization loss that together achieve a $100\times$100× speedup and stable open topology without image input. These disentangled 3D representations are then optimized by specialized expert diffusion models tailored to each domain, ensuring high-fidelity outputs. To mitigate geometric artifacts and texture conflicts when combining different expert models, we further propose several effective geometric losses and strategies. Extensive experiments demonstrate that DreamBarbie outperforms existing methods in both dressed human and outfit generation. Our framework further enables diverse applications, including apparel combination, editing, expressive animation, and physical simulation.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 5144-5155
DreamBarbie: Text to Barbie-Style 3D Avatars
To integrate digital humans into everyday life, there is a strong demand for generating high-quality, fine-grained disentangled 3D avatars that support expressive animation and simulation capabilities, ideally from low-cost textual inputs. Although text-driven 3D avatar generation has made significant progress by leveraging 2D generative priors, existing methods still struggle to fulfill all these requirements simultaneously. To address this challenge, we propose DreamBarbie, a novel text-driven framework for generating animatable 3D avatars with separable shoes, accessories, and simulation-ready garments, truly capturing the iconic "Barbie doll" aesthetic. The core of our framework lies in an expressive 3D representation combined with appropriate modeling constraints. Unlike prior methods, we use G-Shell to uniformly model watertight components (e.g., bodies, shoes) and non-watertight garments. By reformulating boundaries as euclidean field intersections instead of manifold geodesics, we propose an SDF-based initialization and a hole regularization loss that together achieve a $100\times$100× speedup and stable open topology without image input. These disentangled 3D representations are then optimized by specialized expert diffusion models tailored to each domain, ensuring high-fidelity outputs. To mitigate geometric artifacts and texture conflicts when combining different expert models, we further propose several effective geometric losses and strategies. Extensive experiments demonstrate that DreamBarbie outperforms existing methods in both dressed human and outfit generation. Our framework further enables diverse applications, including apparel combination, editing, expressive animation, and physical simulation.
- 22 June 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Spiking pyramid wavelet transformation for high-efficient and low-energy image restoration
- 22 June 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Spiking pyramid wavelet transformation for high-efficient and low-energy image restoration
- Open Access
- 18 May 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (6) , 275
Correction: Scene Prior Filtering for Depth Super-Resolution
- 18 May 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (6) , 275
Open AccessCorrection: Scene Prior Filtering for Depth Super-Resolution
- Top Cited Papers
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-18
From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark
Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To address these issues, we introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Based on this formulation, we propose a novel framework, ERR, which integrates three cooperative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). The ZFE incorporates global priors to learn holistic mappings, the LFR reconstructs the main content by focusing on coarse-scale information, and the HFR adopts our proposed frequency-windowed Kolmogorov-Arnold Network (FW-KAN) to recover fine textures and intricate details for high-fidelity restoration. To further advance research in UHD image restoration, we also construct a large-scale, high-quality benchmark dataset, LSUHDIR, comprising 82,126 UHD images with diverse scenes and rich content. Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module. Project page: https://github.com/NJU-PCALab/ERR.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-18
Top Cited PapersFrom Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark
Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To address these issues, we introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Based on this formulation, we propose a novel framework, ERR, which integrates three cooperative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). The ZFE incorporates global priors to learn holistic mappings, the LFR reconstructs the main content by focusing on coarse-scale information, and the HFR adopts our proposed frequency-windowed Kolmogorov-Arnold Network (FW-KAN) to recover fine textures and intricate details for high-fidelity restoration. To further advance research in UHD image restoration, we also construct a large-scale, high-quality benchmark dataset, LSUHDIR, comprising 82,126 UHD images with diverse scenes and rich content. Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module. Project page: https://github.com/NJU-PCALab/ERR.
- 29 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (5) , 251
Scene Prior Filtering for Depth Super-Resolution
- 29 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (5) , 251
Scene Prior Filtering for Depth Super-Resolution