Related papers: FlowAlign: Trajectory-Regularized, Inversion-Free …
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency…
Drag-based editing within pretrained diffusion model provides a precise and flexible way to manipulate foreground objects. Traditional methods optimize the input feature obtained from DDIM inversion directly, adjusting them iteratively to…
Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have…
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…
We introduce MelodyFlow, an efficient text-controllable high-fidelity music generation and editing model. It operates on continuous latent representations from a low frame rate 48 kHz stereo variational auto encoder codec. Based on a…
Recent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation Sampling (SDS) to train 3D models such as Neural RaRecent…
Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT)…
We present FreeMorph, the first tuning-free method for image morphing that accommodates inputs with different semantics or layouts. Unlike existing methods that rely on finetuning pre-trained diffusion models and are limited by time…
Precise and flexible image editing remains a fundamental challenge in computer vision. Based on the modified areas, most editing methods can be divided into two main types: global editing and local editing. In this paper, we choose the two…
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target…
Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…
The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic…
Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching framework in displacement field space that achieves strong…
We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow…
Many approaches have been proposed to estimate camera poses by directly minimizing photometric error. However, due to the non-convex property of direct alignment, proper initialization is still required for these methods. Many robust norms…
Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent…
Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric…
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…
Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the…
Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may…