Related papers: R3DP: Real-Time 3D-Aware Policy for Embodied Manip…
3D face reconstruction (3DFR) algorithms are based on specific assumptions tailored to the limits and characteristics of the different application scenarios. In this study, we investigate how multiple state-of-the-art 3DFR algorithms can be…
The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…
Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…
3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…
Generating safe motion plans in real-time is a key requirement for deploying robot manipulators to assist humans in collaborative settings. In particular, robots must satisfy strict safety requirements to avoid self-damage or harming nearby…
The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing…
Responsive and accurate facial expression recognition is crucial to human-robot interaction for daily service robots. Nowadays, event cameras are becoming more widely adopted as they surpass RGB cameras in capturing facial expression…
Multi-sensor fusion using LiDAR and RGB cameras significantly enhances 3D object detection task. However, conventional LiDAR sensors perform dense, stateless scans, ignoring the strong temporal continuity in real-world scenes. This leads to…
3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other…
Real-time Three-dimensional (3D) scene representation is a foundational element that supports a broad spectrum of cutting-edge applications, including digital manufacturing, Virtual, Augmented, and Mixed Reality (VR/AR/MR), and the emerging…
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…
Inverse design aims to design the input variables of a physical system to optimize a specified objective function, typically formulated as a search or optimization problem. However, in 3D domains, the design space grows exponentially,…
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding…
Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic…
Manipulation planning is the problem of finding a sequence of robot configurations that involves interactions with objects in the scene, e.g., grasping and placing an object, or more general tool-use. To achieve such interactions,…
Data-efficient training of robust robot policies is the key to unlocking automation in a wide array of novel tasks. Current systems require large volumes of demonstrations to achieve robustness, which is impractical in many applications.…
Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query…
Conventional visuomotor imitation learning usually predicts future robot actions directly in the time domain. Such formulations often have limited physical scene awareness and weak long-horizon memory. In contrast, world-model-based…
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introduce a simple, efficient, and effective two-stage detector,…
Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are…