Related papers: MEgoHand: Multimodal Egocentric Hand-Object Intera…
Generating realistic hand-object interactions (HOI) videos is a significant challenge due to the difficulty of modeling physical constraints (e.g., contact and occlusion between hands and manipulated objects). Current methods utilize HOI…
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…
Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambiguity and often ignores non-verbal deictic cues prevalent in real-world…
Reliable hand mesh reconstruction (HMR) from commonly-used color and depth sensors is challenging especially under scenarios with varied illuminations and fast motions. Event camera is a highly promising alternative for its high dynamic…
Deriving co-speech 3D gestures has seen tremendous progress in virtual avatar animation. Yet, the existing methods often produce stiff and unreasonable gestures with unseen human speech inputs due to the limited 3D speech-gesture data. In…
Image generation has achieved remarkable progress with the development of large-scale text-to-image models, especially diffusion-based models. However, generating human images with plausible details, such as faces or hands, remains…
Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and…
We propose a novel hands-free control framework for the Boston Dynamics Spot robot using the Microsoft HoloLens 2 mixed-reality headset. Enabling accessible robot control is critical for allowing individuals with physical disabilities to…
Grasping assistance is essential for restoring autonomy in individuals with motor impairments, particularly in unstructured environments where object categories and user intentions are diverse and unpredictable. We present OVGrasp, a…
Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…
Head avatars animated by visual signals have gained popularity, particularly in cross-driving synthesis where the driver differs from the animated character, a challenging but highly practical approach. The recently presented MegaPortraits…
Forecasting hand motion and pose from an egocentric perspective is essential for understanding human intention. However, existing methods focus solely on predicting positions without considering articulation, and only when the hands are…
We propose to forecast future hand-object interactions given an egocentric video. Instead of predicting action labels or pixels, we directly predict the hand motion trajectory and the future contact points on the next active object (i.e.,…
Video diffusion models have recently achieved remarkable progress in realism and controllability. However, achieving seamless video translation across different perspectives, such as first-person (egocentric) and third-person (exocentric),…
Predicting human motion is critical for assistive robots and AR/VR applications, where the interaction with humans needs to be safe and comfortable. Meanwhile, an accurate prediction depends on understanding both the scene context and human…
Egocentric vision holds great promises for increasing access to visual information and improving the quality of life for people with visual impairments, with object recognition being one of the daily challenges for this population. While we…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable video reasoning capabilities across diverse tasks. However, their ability to understand human intent at a fine-grained level in egocentric videos remains largely…
We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured…
Assistive visual navigation systems for visually impaired individuals have become increasingly popular thanks to the rise of mobile computing. Most of these devices work by translating visual information into voice commands. In complex…
Egocentric perception enables humans to experience and understand the world directly from their own point of view. Translating exocentric (third-person) videos into egocentric (first-person) videos opens up new possibilities for immersive…