3 papers
cs.CV2025
FreeInsert: Personalized Object Insertion with Geometric and Style Control
Yuhong Zhang, Han Wang, Yiwen Wang +2
Text-to-image diffusion models have made significant progress in image generation, allowing for effortless customized generation. However, existing image editing methods still face…
cs.CV2025
AnimeColor: Reference-based Animation Colorization with Diffusion Transformers
Yuhong Zhang, Liyao Wang, Han Wang +4
Animation colorization plays a vital role in animation production, yet existing methods struggle to achieve color accuracy and temporal consistency. To address these challenges, we…
cs.CV2024
Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior
Han Wang, Xinning Chai, Yiwen Wang +3
Colorizing grayscale images offers an engaging visual experience. Existing automatic colorization methods often fail to generate satisfactory results due to incorrect semantic colo…