80 citations · 102 across the 16 of their papers we have counts for
7 papers · 1 filter
Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
Zhuqiang Lu, Kun Hu, Chaoyue Wang +2
A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene. Recently, there has been an increasing interest in synthesising 360-degree images from…
Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance
Zexin Hu, Kun Hu, Clinton Mo +2
Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality. Recentl…
Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms
Penghui Wen, Kun Hu, Wenxi Yue +3
Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-s…
SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
Wenxi Yue, Jing Zhang, Kun Hu +3
The Segment Anything Model (SAM) is a powerful foundation model that has revolutionised image segmentation. To apply SAM to surgical instrument segmentation, a common approach is t…
Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
Clinton Ansun Mo, Kun Hu, Chengjiang Long +1
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision. The action features are often…
Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase
Lintao Wang, Kun Hu, Lei Bai +3
Synthesizing controllable motion for a character using deep learning has been a promising approach due to its potential to learn a compact model without laborious feature engineeri…
Robust Knowledge Adaptation for Federated Unsupervised Person ReID
Jianfeng Weng, Kun Hu, Tingting Yao +2
Person Re-identification (ReID) has been extensively studied in recent years due to the increasing demand in public security. However, collecting and dealing with sensitive persona…