Yunhan Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yunhan Yang has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Xihui Liu
University of Hong Kong, Hong Kong, Hong Kong
3 shared publications - Chunchao Guo
Tencent, Shenzhen, China
2 shared publications - Ding Liang
VAST, Beijing, China
2 shared publications - Hao Xu
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Yan-Pei Cao
VAST, Beijing, China
2 shared publications - Ying-Tian Liu
VAST, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessPolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-16
OmniLatent: Unified Latent for 3D Part Modeling
3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learns a shared latent space that jointly encodes geometry, deformation, appearance, and binary part IDs, allowing data-rich geometric and visual priors to support data-scarce part learning. Given a single input image, the base model generates geometry, deformation, texture, and surface part IDs in one pass, producing a part-aware 3D asset without a separate segmentation stage. We further tune the pretrained model for two extensions: a point-prompt adapter that maps arbitrary 3D point prompts with binary part IDs into latent tokens for full segmentation, refinement, and part subdivision, and an amodal part completion model that completes partial surface masks into a coherent full-object decomposition through dynamic per-part token allocation, cross-attention to the given geometry latent, and alternating part-local and global attention. Extensive experiments show that OmniLatent produces semantically meaningful part segmentations with precise boundaries, supports interactive part editing, and completes partial part observations while preserving global object consistency.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-16
Open AccessOmniLatent: Unified Latent for 3D Part Modeling
3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learns a shared latent space that jointly encodes geometry, deformation, appearance, and binary part IDs, allowing data-rich geometric and visual priors to support data-scarce part learning. Given a single input image, the base model generates geometry, deformation, texture, and surface part IDs in one pass, producing a part-aware 3D asset without a separate segmentation stage. We further tune the pretrained model for two extensions: a point-prompt adapter that maps arbitrary 3D point prompts with binary part IDs into latent tokens for full segmentation, refinement, and part subdivision, and an amodal part completion model that completes partial surface masks into a coherent full-object decomposition through dynamic per-part token allocation, cross-attention to the given geometry latent, and alternating part-local and global attention. Extensive experiments show that OmniLatent produces semantically meaningful part segmentations with precise boundaries, supports interactive part editing, and completes partial part observations while preserving global object consistency.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessOmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
LegoACE: Autoregressive Construction Engine for Expressive LEGO® Assemblies
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessLegoACE: Autoregressive Construction Engine for Expressive LEGO® Assemblies
- Open Access
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation
Recent advancements in leveraging pre-trained 2D diffusion models achieve the generation of high-quality novel views from a single in-the-wild image. However, existing works face challenges in producing controllable novel views due to the lack of information from multiple views. In this paper, we present DreamComposer++, a flexible and scalable framework designed to improve current view-aware diffusion models by incorporating multi-view conditions. Specifically, DreamComposer++ utilizes a view-aware 3D lifting module to extract 3D representations of an object from various views. These representations are then aggregated and rendered into the latent features of target view through the multi-view feature fusion module. Finally, the obtained features of target view are integrated into pre-trained image or video diffusion models for novel view synthesis. Experimental results demonstrate that DreamComposer++ seamlessly integrates with cutting-edge view-aware diffusion models and enhances their abilities to generate controllable novel views from multi-view conditions. This advancement facilitates controllable 3D object reconstruction and enables a wide range of applications.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Open AccessDreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation
Recent advancements in leveraging pre-trained 2D diffusion models achieve the generation of high-quality novel views from a single in-the-wild image. However, existing works face challenges in producing controllable novel views due to the lack of information from multiple views. In this paper, we present DreamComposer++, a flexible and scalable framework designed to improve current view-aware diffusion models by incorporating multi-view conditions. Specifically, DreamComposer++ utilizes a view-aware 3D lifting module to extract 3D representations of an object from various views. These representations are then aggregated and rendered into the latent features of target view through the multi-view feature fusion module. Finally, the obtained features of target view are integrated into pre-trained image or video diffusion models for novel view synthesis. Experimental results demonstrate that DreamComposer++ seamlessly integrates with cutting-edge view-aware diffusion models and enhances their abilities to generate controllable novel views from multi-view conditions. This advancement facilitates controllable 3D object reconstruction and enables a wide range of applications.