Related papers: SFHand: Learning Embodied Manipulation by Streamin…
We introduce the novel problem of anticipating a time series of future hand masks from egocentric video. A key challenge is to model the stochasticity of future head motions, which globally impact the head-worn camera video analysis. To…
The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild videos has seen significant progress, reconstructing the…
People continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors. While research in egocentric user and scene understanding has focused primarily on motion and…
In 3D hand-object interaction (HOI) tasks, estimating precise joint poses of hands and objects from monocular RGB input remains highly challenging due to the inherent geometric ambiguity of RGB images and the severe mutual occlusions that…
Hand trajectory forecasting from egocentric views is crucial for enabling a prompt understanding of human intentions when interacting with AR/VR systems. However, existing methods handle this problem in a 2D image space which is inadequate…
Reconstructing detailed hand avatars plays a crucial role in various applications. While prior works have focused on capturing high-fidelity hand geometry, they heavily rely on high-resolution multi-view image inputs and struggle to…
Recent studies on 3D hand reconstruction have demonstrated the effectiveness of synthetic training data to improve estimation performance. However, most methods rely on game engines to synthesize hand images, which often lack diversity in…
Emerging applications such as embodied intelligence, AI hardware, autonomous driving, and intelligent cockpits rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding.…
We present EMBED (Egocentric Models Built with Exocentric Data), a method designed to transform exocentric video-language data for egocentric video representation learning. Large-scale exocentric data covers diverse activities with…
We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate modality. In…
Prior works on 3D hand trajectory prediction are constrained by datasets that decouple motion from semantic supervision and by models that weakly link reasoning and action. To address these, we first present the EgoMAN dataset, a…
Understanding a 3D scene immediately with its exploration is essential for embodied tasks, where an agent must construct and comprehend the 3D scene in an online and nearly real-time manner. In this study, we propose EmbodiedSplat, an…
We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high…
Understanding human intentions and actions through egocentric videos is important on the path to embodied artificial intelligence. As a branch of egocentric vision techniques, hand trajectory prediction plays a vital role in comprehending…
Egocentric action anticipation aims to predict the future actions the camera wearer will perform from the observation of the past. While predictions about the future should be available before the predicted events take place, most…
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…
Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid…
We present AssemblyHands, a large-scale benchmark dataset with accurate 3D hand pose annotations, to facilitate the study of egocentric activities with challenging hand-object interactions. The dataset includes synchronized egocentric and…
Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements.…
Human comprehension of a video stream is naturally broad: in a few instants, we are able to understand what is happening, the relevance and relationship of objects, and forecast what will follow in the near future, everything all at once.…