相关论文: Motion-2-To-3: Leveraging 2D Motion Data for 3D Mo…

Embodied human communication encompasses both verbal (speech) and non-verbal information (e.g., gesture and head movements). Recent advances in machine learning have substantially improved the technologies for generating synthetic versions…

Association, aiming to link bounding boxes of the same identity in a video sequence, is a central component in multi-object tracking (MOT). To train association modules, e.g., parametric networks, real video data are usually used. However,…

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…

This paper introduces the first text-guided work for generating the sequence of hand-object interaction in 3D. The main challenge arises from the lack of labeled data where existing ground-truth datasets are nowhere near generalizable in…

We introduce Unimotion, the first unified multi-task human motion model capable of both flexible motion control and frame-level motion understanding. While existing works control avatar motion with global text conditioning, or with…

In 3D Human Motion Prediction (HMP), conventional methods train HMP models with expensive motion capture data. However, the data collection cost of such motion capture data limits the data diversity, which leads to poor generalizability to…

Text to Motion aims to generate human motions from texts. Existing settings rely on limited Action Texts that include action labels, which limits flexibility and practicability in scenarios difficult to describe directly. This paper extends…

We present a framework for video-driven crowd synthesis. Motion vectors extracted from input crowd video are processed to compute global motion paths. These paths encode the dominant motions observed in the input video. These paths are then…

Text-to-motion generation, which translates textual descriptions into human motions, has been challenging in accurately capturing detailed user-imagined motions from simple text inputs. This paper introduces StickMotion, an efficient…

Text-Image-to-Video (TI2V) generation aims to generate a video from an image following a text description, which is also referred to as text-guided image animation. Most existing methods struggle to generate videos that align well with the…

In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models…

Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These…

State-of-the-art text-to-motion generation models rely on the kinematic-aware, local-relative motion representation popularized by HumanML3D, which encodes motion relative to the pelvis and to the previous frame with built-in redundancy.…

Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a…

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

Generating 3D human motions from textual descriptions is an important research problem with broad applications in video games, virtual reality, and augmented reality. Recent methods align the textual description with human motion at the…

Given a video of a person in action, we can easily guess the 3D future motion of the person. In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input. We do this…

One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-art methods are able to synthesize a video demonstrating…

The ability to generate complex and realistic human body animations at scale, while following specific artistic constraints, has been a fundamental goal for the game and animation industry for decades. Popular techniques include…

We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a…