5 papers
MoCha:End-to-End Video Character Replacement without Structural Guidance
Zhengbo Xu, Jie Ma, Ziheng Wang +3
Controllable video character replacement with a user-provided identity remains a challenging problem due to the lack of paired video data. Prior works have predominantly relied on…
Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
Qiang Lyu, Zicong Chen, Chongxiao Wang +9
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical…
SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning
Duoteng Xu, Yuguang Chen, Jing Li +5
Mesh seams play a pivotal role in partitioning 3D surfaces for UV parametrization and texture mapping. Poorly placed seams often result in severe UV distortion or excessive fragmen…
Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
Jian Liu, Jing Xu, Song Guo +10
Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-lev…
StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation
Zhengguang Zhou, Jing Li, Huaxia Li +2
Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the…