5 papers
Single Image, Any Face: Generalisable 3D Face Generation
Wenqing Wang, Haosen Yang, Josef Kittler +1
The creation of 3D human face avatars from a single unconstrained image is a fundamental task that underlies numerous real-world vision and graphics applications. Despite the signi…
MERGETUNE: Continued Fine-Tuning of Vision-Language Models
Wenqing Wang, Da Li, Xiatian Zhu +1
Fine-tuning vision-language models (VLMs) such as CLIP often leads to catastrophic forgetting of pretrained knowledge. Prior work primarily aims to mitigate forgetting during adapt…
Dynamic Avatar-Scene Rendering from Human-centric Context
Wenqing Wang, Haosen Yang, Josef Kittler +1
Reconstructing dynamic humans interacting with real-world environments from monocular videos is an important and challenging task. Despite considerable progress in 4D neural render…
Improving Gaussian Splatting with Localized Points Management
Haosen Yang, Chenhao Zhang, Wenqing Wang +4
Point management is critical for optimizing 3D Gaussian Splatting models, as point initiation (e.g., via structure from motion) is often distributionally inappropriate. Typically,…
Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis
Tao Jun Lin, Wenqing Wang, Yujiao Shi +3
This paper presents a novel approach for cross-view synthesis aimed at generating plausible ground-level images from corresponding satellite imagery or vice versa. We refer to thes…