Related papers: DragAPart: Learning a Part-Level Motion Prior for …

We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level…

Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing…

This paper proposes a novel deep learning framework for multi-modal motion prediction. The framework consists of three parts: recurrent neural networks to process the target agent's motion process, convolutional neural networks to process…

Part assembly is a typical but challenging task in robotics, where robots assemble a set of individual parts into a complete shape. In this paper, we develop a robotic assembly simulation environment for furniture assembly. We formulate the…

Human motion generation from text prompts has made remarkable progress in recent years. However, existing methods primarily rely on either sequence-level or action-level descriptions due to the absence of fine-grained, part-level motion…

Creating believable motions for various characters has long been a goal in computer graphics. Current learning-based motion synthesis methods depend on extensive motion datasets, which are often challenging, if not impossible, to obtain. On…

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…

The articulated and complex nature of human actions makes the task of action recognition difficult. One approach to handle this complexity is dividing it to the kinetics of body parts and analyzing the actions based on these partial…

Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting…

Drag-based image editing has emerged as a powerful paradigm for intuitive image manipulation. However, existing approaches predominantly rely on manipulating the latent space of generative models, leading to limited precision, delayed…

We address the challenge of creating 3D assets for household articulated objects from a single image. Prior work on articulated object creation either requires multi-view multi-state input, or only allows coarse control over the generation…

Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep…

Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper,…

We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part referential language. We exploit the fact that linguistic descriptions of a shape can…

Given a raw video sequence taken from a freely-moving camera, we study the problem of decomposing the observed 3D scene into a static background and a dynamic foreground containing the objects that move in the video sequence. This task is…

Recent advances in object segmentation have demonstrated that deep neural networks excel at object segmentation for specific classes in color and depth images. However, their performance is dictated by the number of classes and objects used…

This work aims to provide a deep-learning solution for the motion interpolation task. Previous studies solve it with geometric weight functions. Some other works propose neural networks for different problem settings with consecutive pose…

A generalist robot equipped with learned skills must be able to perform many tasks in many different environments. However, zero-shot generalization to new settings is not always possible. When the robot encounters a new environment or…

Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization…

We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…