Related papers: HOSIG: Full-Body Human-Object-Scene Interaction Ge…
Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often…
Can we synthesize 3D humans interacting with scenes without learning from any 3D human-scene interaction data? We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of…
Modelling interactions between humans and objects in natural environments is central to many applications including gaming, virtual and mixed reality, as well as human behavior analysis and human-robot collaboration. This challenging…
We propose OVIGo-3DHSG method - Open-Vocabulary Indoor Grounding of objects using 3D Hierarchical Scene Graph. OVIGo-3DHSG represents an extensive indoor environment over a Hierarchical Scene Graph derived from sequences of RGB-D frames…
Text-driven multi-human motion generation with complex interactions remains a challenging problem. Despite progress in performance, existing offline methods that generate fixed-length motions with a fixed number of agents, are inherently…
Reconstructing 3D human-object interaction (HOI) from single-view RGB images is challenging due to the absence of depth information and potential occlusions. Existing methods simply predict the body poses merely rely on network training on…
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…
Accepted in the ICIP 2025 We present a novel transformer-based framework for whole-body grasping that addresses both pose generation and motion infilling, enabling realistic and stable object interactions. Our pipeline comprises three…
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…
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D…
Despite some exciting progress on high-quality image generation from structured(scene graphs) or free-form(sentences) descriptions, most of them only guarantee the image-level semantical consistency, i.e. the generated image matching the…
Despite advances in indoor 3D scene layout generation, synthesizing scenes with dense object arrangements remains challenging. Existing methods focus on large furniture while neglecting smaller objects, resulting in unrealistically empty…
Human dance generation (HDG) aims to synthesize realistic videos from images and sequences of driving poses. Despite great success, existing methods are limited to generating videos of a single person with specific backgrounds, while the…
To address key limitations in human-object interaction (HOI) video generation -- specifically the reliance on curated motion data, limited generalization to novel objects/scenarios, and restricted accessibility -- we introduce…
Enabling mobile robots to perform long-term tasks in dynamic real-world environments is a formidable challenge, especially when the environment changes frequently due to human-robot interactions or the robot's own actions. Traditional…
Effective human-robot interaction requires robots to identify human intentions and generate expressive, socially appropriate motions in real-time. Existing approaches often rely on fixed motion libraries or computationally expensive…
Generating realistic human motions that naturally respond to both spoken language and physical objects is crucial for interactive digital experiences. Current methods, however, address speech-driven gestures or object interactions…
Equipping humanoid robots with versatile interaction skills typically requires either extensive policy training or explicit human-to-robot motion retargeting. However, learning-based policies face prohibitive data collection costs.…
Recent advances in 3D scene representations have enabled high-fidelity novel view synthesis, yet adapting to discrete scene changes and constructing interactive 3D environments remain open challenges in vision and robotics. Existing…
Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This gap is more evident in drone simulators, where simulation environments still rely heavily…