Related papers: HoloMotion-1 Technical Report
Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face significant limitations that hinder their practical…
Recent advances in customized video generation have enabled users to create videos tailored to both specific subjects and motion trajectories. However, existing methods often require complicated test-time fine-tuning and struggle with…
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of…
How do humans move? Advances in reinforcement learning (RL) have produced impressive results in capturing human motion using physics-based humanoid control. However, torque-controlled humanoids fail to model key aspects of human motor…
Humanoid teleoperation plays a vital role in demonstrating and collecting data for complex humanoid-scene interactions. However, current teleoperation systems face critical limitations: they decouple upper- and lower-body control to…
We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric, generative, or simulation priors to guide the transfer…
Recent advancements in large-scale offline training have demonstrated the potential of generalist policy learning for complex robotic tasks. However, applying these principles to legged locomotion remains a challenge due to continuous…
Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces…
We present SLoMo: a first-of-its-kind framework for transferring skilled motions from casually captured "in the wild" video footage of humans and animals to legged robots. SLoMo works in three stages: 1) synthesize a physically plausible…
Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle only one motion type or rely on ambiguous 2D cues that entangle camera-induced parallax with…
Humanoid motion control has witnessed significant breakthroughs in recent years, with deep reinforcement learning (RL) emerging as a primary catalyst for achieving complex, human-like behaviors. However, the high dimensionality and…
The deployment of humanoid robots for dexterous manipulation in unstructured environments remains challenging due to perceptual limitations that constrain the effective workspace. In scenarios where physical constraints prevent the robot…
Humans' ability to smoothly switch between locomotion and manipulation is a remarkable feature of sensorimotor coordination. Leaning and replication of such human-like strategies can lead to the development of more sophisticated robots…
Accurately analyzing the motion parts and their motion attributes in dynamic environments is crucial for advancing key areas such as embodied intelligence. Addressing the limitations of existing methods that rely on dense multi-view images…
Teleoperating humanoid robots in a whole-body manner marks a fundamental step toward developing general-purpose robotic intelligence, with human motion providing an ideal interface for controlling all degrees of freedom. Yet, most current…
Human motion prediction is a complex task as it involves forecasting variables over time on a graph of connected sensors. This is especially true in the case of few-shot learning, where we strive to forecast motion sequences for previously…
Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, due to the challenges in data collection and network designs, it remains challenging for…
Human motion recovery for real-world interaction demands both precise action details and metric-scale trajectories. Recovering absolute human pose from monocular input presents a viable solution, but faces two main challenges: (1) models'…
Motion imitation is a promising approach for humanoid locomotion, enabling agents to acquire humanlike behaviors. Existing methods typically rely on high-quality motion capture datasets such as AMASS, but these are scarce and expensive,…
Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perception noise that degrades performance on fine-grained tasks, and training a unified policy…