6 papers
FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
Wenshuo Gao, Junyi Fan, Jiangyue Zeng +1
Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal co…
LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors
Wenshuo Gao, Xicheng Lan, Luyao Zhang +1
Vector graphics, known for their scalability and user-friendliness, provide a unique approach to visual content compared to traditional pixel-based images. Animation of these graph…
ANYPORTAL: Zero-Shot Consistent Video Background Replacement
Wenshuo Gao, Xicheng Lan, Shuai Yang
Despite the rapid advancements in video generation technology, creating high-quality videos that precisely align with user intentions remains a significant challenge. Existing meth…
Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution
Xiaobao Wei, Changyong Shu, Zhaokun Yue +8
High-performance real-time stereo matching methods invariably rely on 3D regularization of the cost volume, which is unfriendly to mobile devices. And 2D regularization based metho…
Training-Free Watermarking for Autoregressive Image Generation
Yu Tong, Zihao Pan, Shuai Yang +1
Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly desi…
Balanced Image Stylization with Style Matching Score
Yuxin Jiang, Liming Jiang, Shuai Yang +3
We present Style Matching Score (SMS), a novel optimization method for image stylization with diffusion models. Balancing effective style transfer with content preservation is a lo…