Related papers: Motion In-Betweening for Densely Interacting Chara…

Human motion synthesis in complex scenes presents a fundamental challenge, extending beyond conventional Text-to-Motion tasks by requiring the integration of diverse modalities such as static environments, movable objects, natural language…

We present a novel approach for the task of human pose transfer, which aims at synthesizing a new image of a person from an input image of that person and a target pose. We address the issues of limited correspondences identified between…

Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films. To this end, deep neural networks drive most recent advances through deep learning and deep…

Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after…

Over the last few decades, many aspects of human life have been enhanced with virtual domains, from the advent of digital assistants such as Amazon's Alexa and Apple's Siri to the latest metaverse efforts of the rebranded Meta. These trends…

Text-to-motion (T2M) generation has broad applications in character animation, virtual avatars, and human-robot interaction. Existing methods typically generate pose trajectories or motion tokens directly from language, forcing a single…

We present a filter based approach for inbetweening. We train a convolutional neural network to generate intermediate frames. This network aim to generate smooth animation of line drawings. Our method can process scanned images directly.…

Developing robotic systems capable of robustly executing long-horizon manipulation tasks with human-level dexterity is challenging, as such tasks require both physical dexterity and seamless sequencing of manipulation skills while robustly…

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches…

Motion understanding aims to establish a reliable mapping between motion and action semantics, while it is a challenging many-to-many problem. An abstract action semantic (i.e., walk forwards) could be conveyed by perceptually diverse…

Existing automatic approaches for 3D virtual character motion synthesis supporting scene interactions do not generalise well to new objects outside training distributions, even when trained on extensive motion capture datasets with diverse…

Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders,…

We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse…

Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which…

We address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a specific object, which outputs the distance to the valid interaction…

Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision. The action features are often derivable accurately from the full series of keyframes, and…

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints…

Artificial quantum systems with synthetic dimensions enable exploring novel quantum phenomena difficult to create in conventional materials. These synthetic degrees of freedom increase the system's dimensionality without altering its…

3D hand-object pose estimation is the key to the success of many computer vision applications. The main focus of this task is to effectively model the interaction between the hand and an object. To this end, existing works either rely on…

Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging. Existing methods tend to generate limited sub-actions or incoherent…