Mingxiao Tu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mingxiao Tu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Andre Z. Kyme
The University of Sydney
2 shared publications - Hoijoon Jung
School of Computer Science, The University of Sydney, Sydney, NSW, Australia
2 shared publications - Jinman Kim
The University of Sydney
2 shared publications - Shuchang Ye
The University of Sydney
1 shared publication
Latest Publications
- Open Access
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (10) , 1-11
SMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis with World Knowledge Transfer from GPT via Geometry-Aware Projection
Texturing 3D human avatars from natural-language prompts remains challenging because generated UV texture maps must be both high-quality and semantically consistent with the prompt. Prior work typically re-trains generative adversarial or diffusion models on curated datasets, which constrain generalization to clothing, stylistic, and cultural variations present in those datasets. To address these limitations, we present SMPL-GPTexture, a training-free pipeline that leverages the rich world knowledge of a pre-trained GPT model to synthesize SMPL human textures. Given a tailored natural-language prompt, GPT- 4o generates geometry-consistent front/back views; we fit SMPL to each view, and invert-rasterize colours into canonical UV space with a geometry-aware view-quality weight, and close remaining gaps with diffusion-based inpainting. On a 550-prompt benchmark, SMPL-GPTexture achieves +17.6% CLIP similarity and +22.4% BLIP improvement over state-of-the-art text-to-texture methods while reducing visible seam artifacts. It generalizes to diverse scenarios such as fantasy avatars, stylized body art, and specialized uniforms without domain-specific finetuning. This facilitates the generation of high-quality textures that surpass current text-to-texture pipelines for fashion prototyping, AR telepresence and digital asset generation. We open-source a UV texture map dataset that covers 23 artistic styles, 49 professions, 19 ethnicities, and 67 clothing descriptors, and a set of easily adaptable prompt templates that can be repurposed to generate any desired texture, fostering research on prompt-driven avatar appearance. The code, sample dataset and prompts will be available at https://github.com/DavidTu21/SMPL-GPTexture.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (10) , 1-11
Open AccessSMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis with World Knowledge Transfer from GPT via Geometry-Aware Projection
Texturing 3D human avatars from natural-language prompts remains challenging because generated UV texture maps must be both high-quality and semantically consistent with the prompt. Prior work typically re-trains generative adversarial or diffusion models on curated datasets, which constrain generalization to clothing, stylistic, and cultural variations present in those datasets. To address these limitations, we present SMPL-GPTexture, a training-free pipeline that leverages the rich world knowledge of a pre-trained GPT model to synthesize SMPL human textures. Given a tailored natural-language prompt, GPT- 4o generates geometry-consistent front/back views; we fit SMPL to each view, and invert-rasterize colours into canonical UV space with a geometry-aware view-quality weight, and close remaining gaps with diffusion-based inpainting. On a 550-prompt benchmark, SMPL-GPTexture achieves +17.6% CLIP similarity and +22.4% BLIP improvement over state-of-the-art text-to-texture methods while reducing visible seam artifacts. It generalizes to diverse scenarios such as fantasy avatars, stylized body art, and specialized uniforms without domain-specific finetuning. This facilitates the generation of high-quality textures that surpass current text-to-texture pipelines for fashion prototyping, AR telepresence and digital asset generation. We open-source a UV texture map dataset that covers 23 artistic styles, 49 professions, 19 ethnicities, and 67 clothing descriptors, and a set of easily adaptable prompt templates that can be repurposed to generate any desired texture, fostering research on prompt-driven avatar appearance. The code, sample dataset and prompts will be available at https://github.com/DavidTu21/SMPL-GPTexture.
- Open Access
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (2) , 1165-1175
Head-Mounted Displays in Context-Aware Systems for Open Surgery: A State-of-the-Art Review
Surgical context-aware systems (SCAS), which leverage real-time data and analysis from the operating room to inform surgical activities, can be enhanced through the integration of head-mounted displays (HMDs). Rather than user-agnostic data derived from conventional, and often static, external sensors, HMD-based SCAS relies on dynamic user-centric sensing of the surgical context. The analyzed context-aware information is then augmented directly into a user's field of view via augmented reality (AR) to directly improve their task and decision-making capability. This stateof-the-art review complements previous reviews by exploring the advancement of HMD-based SCAS, including their development and impact on enhancing situational awareness and surgical outcomes in the operating room. The survey demonstrates that this technology can mitigate risks associated with gaps in surgical expertise, increase procedural efficiency, and improve patient outcomes. We also highlight key limitations still to be addressed by the research community, including improving prediction accuracy, robustly handling data heterogeneity, and reducing system latency.
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (2) , 1165-1175
Open AccessHead-Mounted Displays in Context-Aware Systems for Open Surgery: A State-of-the-Art Review
Surgical context-aware systems (SCAS), which leverage real-time data and analysis from the operating room to inform surgical activities, can be enhanced through the integration of head-mounted displays (HMDs). Rather than user-agnostic data derived from conventional, and often static, external sensors, HMD-based SCAS relies on dynamic user-centric sensing of the surgical context. The analyzed context-aware information is then augmented directly into a user's field of view via augmented reality (AR) to directly improve their task and decision-making capability. This stateof-the-art review complements previous reviews by exploring the advancement of HMD-based SCAS, including their development and impact on enhancing situational awareness and surgical outcomes in the operating room. The survey demonstrates that this technology can mitigate risks associated with gaps in surgical expertise, increase procedural efficiency, and improve patient outcomes. We also highlight key limitations still to be addressed by the research community, including improving prediction accuracy, robustly handling data heterogeneity, and reducing system latency.