5 papers
VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis
Zeren Xiong, Yue Yu, Zedong Zhang +3
Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creat…
AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping
Zedong Zhang, Ying Tai, Jianjun Qian +2
Fusing cross-category objects to a single coherent object has gained increasing attention in text-to-image (T2I) generation due to its broad applications in virtual reality, digita…
When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
Wenxuan Fang, Jili Fan, Chao Wang +5
Adverse Weather Image Restoration (AWIR) is a highly challenging task due to the unpredictable and dynamic nature of weather-related degradations. Traditional task-specific methods…
Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion
Zeren Xiong, Zikun Chen, Zedong Zhang +4
In this paper, we tackle a new task of 3D object synthesis, where a 3D model is composited with another object category to create a novel 3D model. However, most existing text/imag…
Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking
Xiantao Hu, Ying Tai, Xu Zhao +5
Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing mult…