Related papers: FantasyHSI: Video-Generation-Centric 4D Human Synt…
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…
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…
Modeling and generating 3D human-object interactions from text is crucial for applications in AR, XR, and gaming. Existing approaches often rely on score distillation from text-to-image models, but their results suffer from the Janus…
In this work, we propose a framework that creates a lively virtual dynamic scene with contextual motions of multiple humans. Generating multi-human contextual motion requires holistic reasoning over dynamic relationships among human-human…
Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods have made significant progress, they struggle to generalize…
Movement is how people interact with and affect their environment. For realistic character animation, it is necessary to synthesize such interactions between virtual characters and their surroundings. Despite recent progress in character…
Realistic scene-level multi-agent motion simulations are crucial for developing and evaluating self-driving algorithms. However, most existing works focus on generating trajectories for a certain single agent type, and typically ignore the…
Real-world human-built environments are highly dynamic, involving multiple humans and their complex interactions with surrounding objects. While 3D geometry modeling of such scenes is crucial for applications like AR/VR, gaming, and…
Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plausible locations and scales without interpenetration, aligning…
Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications. However, collecting massive and annotated real-world human datasets has been a laborious…
Generating human-object interactions (HOIs) is critical with the tremendous advances of digital avatars. Existing datasets are typically limited to humans interacting with a single object while neglecting the ubiquitous manipulation of…
While diffusion models and large-scale motion datasets have advanced text-driven human motion synthesis, extending these advances to 4D human-object interaction (HOI) remains challenging, mainly due to the limited availability of…
Advances in the state of the art for 3d human sensing are currently limited by the lack of visual datasets with 3d ground truth, including multiple people, in motion, operating in real-world environments, with complex illumination or…
Converting process sketches into executable simulation models remains a major bottleneck in process systems engineering, requiring substantial manual effort and simulator-specific expertise. Recent advances in generative AI have improved…
Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are slow (~20s), while feed-forward approaches are fast yet lack…
Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are…
Accurate trajectory prediction is fundamental to autonomous driving, as it underpins safe motion planning and collision avoidance in complex environments. However, existing benchmark datasets suffer from a pronounced long-tail distribution…
The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for…
The significant progress on Generative Adversarial Networks (GANs) has facilitated realistic single-object image generation based on language input. However, complex-scene generation (with various interactions among multiple objects) still…
Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate…