Zhengming Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhengming Yu has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Wenping Wang
Texas A&M University, College Station, USA
7 shared publications - Xin Li
Texas A&M University, College Station, USA
7 shared publications - Jionghao Wang
Texas A&M University, College Station, USA
4 shared publications - Yuan Liu
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
4 shared publications - Cheng Lin
Macau University of Science and Technology, Macau, Macao
3 shared publications - Jingdong Zhang
Texas A&M University, College Station, USA
3 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessRecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
- 2 October 2026
- Published by Springer Nature
- p. 336-357
DiffHDR: Re-exposing LDR Videos with Video Diffusion Models
- 2 October 2026
- Published by Springer Nature
- p. 336-357
DiffHDR: Re-exposing LDR Videos with Video Diffusion Models
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors
Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While perspective foundation models have achieved success through data scaling, directly adapting them to the panoramic domain often fails due to severe geometric distortions and coordinate system discrepancies. Furthermore, the underlying relations between diverse dense prediction tasks in spherical spaces are underexplored. To address these challenges, we propose MTPano, a robust multi-task panoramic foundation model established by a label-free training pipeline. First, to circumvent data scarcity, we leverage powerful perspective dense priors. We project panoramic images into perspective patches to generate accurate, domain-gap-free pseudo-labels using off-the-shelf foundation models, which are then re-projected to serve as patch-wise supervision. Second, to tackle the interference between task types, we categorize tasks into rotation-invariant (e.g., depth, segmentation) and rotation-variant (e.g., surface normals) groups. We introduce the Panoramic Dual BridgeNet (PD-BridgeNet), which disentangles these feature streams via geometry-aware modulation layers that inject absolute position and ray direction priors. To handle the distortion from equirectangular projections (ERP), we incorporate ERP token mixers followed by a dual-branch BridgeNet for interactions with gradient truncation, facilitating beneficial cross-task information sharing while blocking conflicting gradients from incompatible task attributes. Additionally, we introduce auxiliary tasks (image gradient, edge distance field, point map estimation) to fertilize the cross-task learning process. Extensive experiments demonstrate that MTPano achieves state-of-the-art performance on multiple benchmarks and delivers competitive results against task-specific panoramic specialist foundation models. Code and model is released at https://github.com/Evergreen0929/MTPano.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessMTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors
Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While perspective foundation models have achieved success through data scaling, directly adapting them to the panoramic domain often fails due to severe geometric distortions and coordinate system discrepancies. Furthermore, the underlying relations between diverse dense prediction tasks in spherical spaces are underexplored. To address these challenges, we propose MTPano, a robust multi-task panoramic foundation model established by a label-free training pipeline. First, to circumvent data scarcity, we leverage powerful perspective dense priors. We project panoramic images into perspective patches to generate accurate, domain-gap-free pseudo-labels using off-the-shelf foundation models, which are then re-projected to serve as patch-wise supervision. Second, to tackle the interference between task types, we categorize tasks into rotation-invariant (e.g., depth, segmentation) and rotation-variant (e.g., surface normals) groups. We introduce the Panoramic Dual BridgeNet (PD-BridgeNet), which disentangles these feature streams via geometry-aware modulation layers that inject absolute position and ray direction priors. To handle the distortion from equirectangular projections (ERP), we incorporate ERP token mixers followed by a dual-branch BridgeNet for interactions with gradient truncation, facilitating beneficial cross-task information sharing while blocking conflicting gradients from incompatible task attributes. Additionally, we introduce auxiliary tasks (image gradient, edge distance field, point map estimation) to fertilize the cross-task learning process. Extensive experiments demonstrate that MTPano achieves state-of-the-art performance on multiple benchmarks and delivers competitive results against task-specific panoramic specialist foundation models. Code and model is released at https://github.com/Evergreen0929/MTPano.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Promoting LDR Panoramas to HDRI with Rendering-Space Losses
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessPromoting LDR Panoramas to HDRI with Rendering-Space Losses
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessGAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians
- 29 November 2024
- Published by Springer Nature
- p. 381-401
Disentangled Clothed Avatar Generation from Text Descriptions
- 29 November 2024
- Published by Springer Nature
- p. 381-401
Disentangled Clothed Avatar Generation from Text Descriptions
- 3 October 2024
- Published by Springer Nature
- p. 419-438
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
- 3 October 2024
- Published by Springer Nature
- p. 419-438
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models