25 citations · 40 across the 18 of their papers we have counts for
8 papers · 2 filters
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…
3D Audio-Visual Segmentation
Artem Sokolov, Swapnil Bhosale, Xiatian Zhu
Recognizing the sounding objects in scenes is a longstanding objective in embodied AI, with diverse applications in robotics and AR/VR/MR. To that end, Audio-Visual Segmentation (A…
FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
Xi Chen, Haosen Yang, Sheng Jin +2
Open-vocabulary segmentation poses significant challenges, as it requires segmenting and recognizing objects across an open set of categories in unconstrained environments. Buildin…
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…
MacFormer: Semantic Segmentation with Fine Object Boundaries
Guoan Xu, Wenfeng Huang, Tao Wu +5
Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segme…
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,…
Unsupervised Audio-Visual Segmentation with Modality Alignment
Swapnil Bhosale, Haosen Yang, Diptesh Kanojia +2
Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained anno…
Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation
Xi Chen, Haosen Yang, Huicong Zhang +2
Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data. Self-tr…