5 papers
h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform
Zehui Guo, Zhen Wang, Junwei Shu +3
Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original i…
Bridging Rendering and Generative Modeling with Monte Carlo Transport Scheduling
Junwei Shu, Wenjie Liu, Hantang Liu +2
Monte Carlo rendering and modern generative models both transform uncertain states into structured images, yet they are usually studied as separate processes. We introduce Monte Ca…
GT2-GS: Geometry-aware Texture Transfer for Gaussian Splatting
Wenjie Liu, Zhongliang Liu, Junwei Shu +2
Transferring 2D textures onto complex 3D scenes plays a vital role in enhancing the efficiency and controllability of 3D multimedia content creation. However, existing 3D style tra…
LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer
Changgu Chen, Xiaoyan Yang, Junwei Shu +2
In recent years, large-scale pre-trained diffusion transformer models have made significant progress in video generation. While current DiT models can produce high-definition, high…
Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation
Changgu Chen, Junwei Shu, Gaoqi He +2
Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting co…