Wanjun Lv
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wanjun Lv has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Liuxin Zhang
Lenovo Research, Beijing, China
2 shared publications - Duotun Wang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
1 shared publication - Fangfei Gou
Key Laboratory of Pervasive Computing, Ministry of Education, Global Innovation Exchange (GIX) Institute, Tsinghua University, Beijing, China
1 shared publication - Haoran Duan
Department of Automation, Tsinghua University, Beijing, China
1 shared publication - Jin Wei
Lenovo Research, Beijing, China
1 shared publication - Jungong Han
The University of Sheffield
1 shared publication
Latest Publications
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4802-4815
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
Recent advances in zero-shot text-to-3D generation have revolutionised 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods leverage 3D Gaussian Splatting with score distillation to enhance multi-view rendering through pre-trained text-to-image (T2I) models, they suffer from inherent prior view biases in T2I Models. These biases lead to inconsistent 3D generation, particularly manifesting as the multi-face Janus problem, where objects exhibit conflicting features across views. To address this fundamental challenge, we propose ConsDreamer, a novel method that mitigates view bias by refining both the conditional and unconditional terms in the score distillation process: (1) a View Disentanglement Module (VDM) that eliminates viewpoint biases in conditional prompts by decoupling irrelevant view components and injecting precise view control; and (2) a similarity-based partial order loss that enforces geometric consistency in the unconditional term by aligning cosine similarities with azimuth relationships. Extensive experiments demonstrate that ConsDreamer can be seamlessly integrated into various 3D representations and score distillation paradigms, effectively mitigating the multi-face Janus problem.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4802-4815
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
Recent advances in zero-shot text-to-3D generation have revolutionised 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods leverage 3D Gaussian Splatting with score distillation to enhance multi-view rendering through pre-trained text-to-image (T2I) models, they suffer from inherent prior view biases in T2I Models. These biases lead to inconsistent 3D generation, particularly manifesting as the multi-face Janus problem, where objects exhibit conflicting features across views. To address this fundamental challenge, we propose ConsDreamer, a novel method that mitigates view bias by refining both the conditional and unconditional terms in the score distillation process: (1) a View Disentanglement Module (VDM) that eliminates viewpoint biases in conditional prompts by decoupling irrelevant view components and injecting precise view control; and (2) a similarity-based partial order loss that enforces geometric consistency in the unconditional term by aligning cosine similarities with azimuth relationships. Extensive experiments demonstrate that ConsDreamer can be seamlessly integrated into various 3D representations and score distillation paradigms, effectively mitigating the multi-face Janus problem.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
3D-MAGIC: Expanding MAGIC Pointing to Stereoscopic Displays
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open Access3D-MAGIC: Expanding MAGIC Pointing to Stereoscopic Displays
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
HybridDeform4D: Joint Refinement of Mesh and Gaussian Splatting for Video-to-4D Object Generation
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessHybridDeform4D: Joint Refinement of Mesh and Gaussian Splatting for Video-to-4D Object Generation
- 1 December 2024
- Published by Springer Nature
- p. 211-226
MRCI: Multi-range Context Interaction for Boundary Refinement in Image Segmentation
- 1 December 2024
- Published by Springer Nature
- p. 211-226
MRCI: Multi-range Context Interaction for Boundary Refinement in Image Segmentation