相关论文: TSTMotion: Training-free Scene-aware Text-to-motio…

Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural…

Text-to-motion (T2M) generation aims to control the behavior of a target character via textual descriptions. Leveraging text-motion paired datasets, existing T2M models have achieved impressive performance in generating high-quality motions…

Human auditory perception is shaped by moving sound sources in 3D space, yet prior work in generative sound modelling has largely been restricted to mono signals or static spatial audio. In this work, we introduce a framework for generating…

We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training data. By leveraging a few video samples demonstrating…

Enabling humanoid robots to synthesize complex, physically coherent motions from natural language commands is a cornerstone of autonomous robotics and human-robot interaction. While diffusion models have shown promise in this text-to-motion…

In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to…

In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs).…

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

Human communication is inherently multimodal, involving a combination of verbal and non-verbal cues such as speech, facial expressions, and body gestures. Modeling these behaviors is essential for understanding human interaction and for…

Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs, failing to capture complex motions described by text. This…

Motion synthesis for diverse object categories holds great potential for 3D content creation but remains underexplored due to two key challenges: (1) the lack of comprehensive motion datasets that include a wide range of high-quality…

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…

Well-designed indoor scenes should prioritize how people can act within a space rather than merely what objects to place. However, existing 3D scene generation methods emphasize visual and semantic plausibility, while insufficiently…

The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated videos may present artifacts, including structural…

Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system…

We introduce a method to synthesize animator guided human motion across 3D scenes. Given a set of sparse (3 or 4) joint locations (such as the location of a person's hand and two feet) and a seed motion sequence in a 3D scene, our method…

Text-image-to-video (TI2V) generation is a critical problem for controllable video generation using both semantic and visual conditions. Most existing methods typically add visual conditions to text-to-video (T2V) foundation models by…

In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e.g., ``A person walks forward"). Existing techniques struggle with motion diversity and smooth transitions in…

We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text-driven methods that often suffer from geometric drift or…

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…