2 citations · 2 across the 6 of their papers we have counts for
6 papers
RMLer: Synthesizing Novel Objects across Diverse Categories via Reinforcement Mixing Learning
Jun Li, Zikun Chen, Haibo Chen +2
Novel object synthesis by integrating distinct textual concepts from diverse categories remains a significant challenge in Text-to-Image (T2I) generation. Existing methods often su…
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…
WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning
Wenxuan Fang, Jiangwei Weng, Jianjun Qian +2
Unsupervised image restoration under multi-weather conditions remains a fundamental yet underexplored challenge. While existing methods often rely on task-specific physical priors,…
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…