相关论文: One-shot Video Imitation via Parameterized Symboli…

Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network is attracting significant attention. In this paper, we introduce a "3D as-smooth-as-possible (3D-ASAP)" prior inside the…

Parametric 3D models have formed a fundamental role in modeling deformable objects, such as human bodies, faces, and hands; however, the construction of such parametric models requires significant manual intervention and domain expertise.…

Robotic grasping traditionally relies on object features or shape information for learning new or applying already learned grasps. We argue however that such a strong reliance on object geometric information renders grasping and grasp…

With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties. While these approaches have improved performance in graph machine learning tasks compared to…

Semantics has enabled 3D scene understanding and affordance-driven object interaction. However, robots operating in real-world environments face a critical limitation: they cannot anticipate how objects move. Long-horizon mobile…

This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key…

Capturing scene dynamics and predicting the future scene state is challenging but essential for robotic manipulation tasks, especially when the scene contains both rigid and deformable objects. In this work, we contribute a simulation…

Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance. Activity…

Deformable objects often appear in unstructured configurations. Tracing deformable objects helps bringing them into extended states and facilitating the downstream manipulation tasks. Due to the requirements for object-specific modeling or…

Combining accurate geometry with rich semantics has been proven to be highly effective for language-guided robotic manipulation. Existing methods for dynamic scenes either fail to update in real-time or rely on additional depth sensors for…

In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we…

As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency detection is how to…

A key challenge in robotic food manipulation is modeling the material properties of diverse and deformable food items. We propose using a multimodal sensory approach to interact and play with food that facilitates the ability to distinguish…

Robotic manipulation in unstructured environments requires reliable execution under diverse conditions, yet many state-of-the-art systems still struggle with high-dimensional action spaces, sparse rewards, and slow generalization beyond…

Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…

Cinemagraphs are a compelling way to convey dynamic aspects of a scene. In these media, dynamic and still elements are juxtaposed to create an artistic and narrative experience. Creating a high-quality, aesthetically pleasing cinemagraph…

3D Gaussian Splatting has achieved remarkable success in reconstructing both static and dynamic 3D scenes. However, in a scene represented by 3D Gaussian primitives, interactions between objects suffer from inaccurate 3D segmentation,…

Interactive grasping from clutter, akin to human dexterity, is one of the longest-standing problems in robot learning. Challenges stem from the intricacies of visual perception, the demand for precise motor skills, and the complex interplay…

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…

Modeling and recognition of surgical activities poses an interesting research problem. Although a number of recent works studied automatic recognition of surgical activities, generalizability of these works across different tasks and…