Related papers: BeyondMimic: From Motion Tracking to Versatile Hum…
Human motion generation is a significant pursuit in generative computer vision with widespread applications in film-making, video games, AR/VR, and human-robot interaction. Current methods mainly utilize either diffusion-based generative…
We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training.…
We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across…
Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while…
Diffusion models have recently been successfully applied to a wide range of robotics applications for learning complex multi-modal behaviors from data. However, prior works have mostly been confined to single-robot and small-scale…
Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same…
Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…
We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use…
Recent work has explored a range of model families for human motion generation, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and diffusion-based models. Despite their differences, many methods rely on…
We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations into structured robot states-such as 3D keypoints or joint…
Predicting human gaze scanpaths is crucial for understanding visual attention, with applications in human-computer interaction, autonomous systems, and cognitive robotics. While deep learning models have advanced scanpath prediction, most…
Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps. Thus, they can easily generalize and adapt to new and changing environments. Current Imitation Learning…
Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in robotics, especially in robot manipulations. Diffusion models…
Despite the ability of existing large-scale text-to-image (T2I) models to generate high-quality images from detailed textual descriptions, they often lack the ability to precisely edit the generated or real images. In this paper, we propose…
Long-range human movement generation remains a central challenge in computer vision and graphics. Generating coherent transitions across semantically distinct motion domains remains largely unexplored. This capability is particularly…
Diffusion-based visuomotor policies effectively capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control. Recent flow matching and consistency-based methods…
Generating realistic motions for digital humans is a core but challenging part of computer animations and games, as human motions are both diverse in content and rich in styles. While the latest deep learning approaches have made…
Recent advancements utilizing large-scale video data for learning video generation models demonstrate significant potential in understanding complex physical dynamics. It suggests the feasibility of leveraging diverse robot trajectory data…
Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint…
Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly. We propose Diffusion-SAFE, a closed-loop framework built on two diffusion models: an…