Related papers: REWIND: Real-Time Egocentric Whole-Body Motion Dif…
Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout,…
Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They…
Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining…
Recent generative models can synthesize high-quality images, but they often fail to generate humans interacting with objects using their hands. This arises mostly from the model's misunderstanding of such interactions and the hardships of…
Human shape editing enables controllable transformation of a person's body shape, such as thin, muscular, or overweight, while preserving pose, identity, clothing, and background. Unlike human pose editing, which has advanced rapidly, shape…
Diffusion models usher a new era of video editing, flexibly manipulating the video contents with text prompts. Despite the widespread application demand in editing human-centered videos, these models face significant challenges in handling…
Diffusion inversion is a task of recovering the noise of an image in a diffusion model, which is vital for controllable diffusion image editing. At present, diffusion inversion still remains a challenging task due to the lack of viable…
Egocentric interactive world models are essential for augmented reality and embodied AI, where visual generation must respond to user input with low latency, geometric consistency, and long-term stability. We study egocentric interaction…
Diffusion models (DMs) have been successfully applied to real image editing. These models typically invert images into latent noise vectors used to reconstruct the original images (known as inversion), and then edit them during the…
Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolution depends…
Rapid urbanization demands accurate and efficient monitoring of turbulent wind patterns to support air quality, climate resilience and infrastructure design. Traditional sparse reconstruction and sensor placement strategies face major…
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without…
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an…
Human intention detection with hand motion prediction is critical to drive the upper-extremity assistive robots in neurorehabilitation applications. However, the traditional methods relying on physiological signal measurement are…
Recent progress in 3D reconstruction has made it easy to create realistic digital twins from everyday environments. However, current digital twins remain largely static and are limited to navigation and view synthesis without embodied…
Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D…
Effectively modeling the interaction between human hands and objects is challenging due to the complex physical constraints and the requirement for high generation efficiency in applications. Prior approaches often employ computationally…
DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging selected points. The method claims that accurate spatial control can be achieved by optimizing…
Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…
Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both…