33 citations · 42 across the 11 of their papers we have counts for
11 papers
RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation
Peizheng Li, Xin Ai, Hanyuan Liu +2
Real-world image generation often involves multi-turn editing, where users iteratively modify small regions while most image content remains unchanged. However, existing diffusion…
Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering
Yun Xing, Hanyuan Liu, Jiahao Nie +1
Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle region-level perception guide…
See-through: Single-image Layer Decomposition for Anime Characters
Jian Lin, Chengze Li, Haoyun Qin +5
We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. Current professional workflows require tedious manual segme…
Hyperstroke: A Novel High-quality Stroke Representation for Assistive Artistic Drawing
Haoyun Qin, Jian Lin, Hanyuan Liu +2
Assistive drawing aims to facilitate the creative process by providing intelligent guidance to artists. Existing solutions often fail to effectively model intricate stroke details…
ToonCrafter: Generative Cartoon Interpolation
Jinbo Xing, Hanyuan Liu, Menghan Xia +4
We introduce ToonCrafter, a novel approach that transcends traditional correspondence-based cartoon video interpolation, paving the way for generative interpolation. Traditional me…
Highly Detailed and Temporal Consistent Video Stylization via Synchronized Multi-Frame Diffusion
Minshan Xie, Hanyuan Liu, Chengze Li +1
Text-guided video-to-video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text-guided image diffusion…
Text-Guided Texturing by Synchronized Multi-View Diffusion
Yuxin Liu, Minshan Xie, Hanyuan Liu +1
This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existi…
Video Colorization with Pre-trained Text-to-Image Diffusion Models
Hanyuan Liu, Minshan Xie, Jinbo Xing +2
Video colorization is a challenging task that involves inferring plausible and temporally consistent colors for grayscale frames. In this paper, we present ColorDiffuser, an adapta…
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Jinbo Xing, Menghan Xia, Yuxin Liu +9
Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential t…
Improved Diffusion-based Image Colorization via Piggybacked Models
Hanyuan Liu, Jinbo Xing, Minshan Xie +2
Image colorization has been attracting the research interests of the community for decades. However, existing methods still struggle to provide satisfactory colorized results given…
Mitigating Congestion in Complex Transportation Networks via Maximum Entropy
Yuhang Fan, Hanyuan Liu, Shibo He
In this paper, we reveal the relationship between entropy rate and the congestion in complex network and solve it analytically for special cases. Finding maximizing entropy rate wi…