6 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…
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,…
Recognize Any Regions
Haosen Yang, Chuofan Ma, Bin Wen +3
Understanding the semantics of individual regions or patches of unconstrained images, such as open-world object detection, remains a critical yet challenging task in computer visio…
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
Swapnil Bhosale, Haosen Yang, Diptesh Kanojia +2
Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have propos…
FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
Haosen Yang, Adrian Bulat, Isma Hadji +4
Diffusion models are proficient at generating high-quality images. They are however effective only when operating at the resolution used during training. Inference at a scaled reso…