Related papers: SceneSmith: Agentic Generation of Simulation-Ready…

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures…

Haptic feedback contributes to immersive virtual reality (VR) experiences. However, designing such feedback at scale for all objects within a VR scene remains time-consuming. We present Scene2Hap, an LLM-centered system that automatically…

We contribute the Habitat Synthetic Scene Dataset, a dataset of 211 high-quality 3D scenes, and use it to test navigation agent generalization to realistic 3D environments. Our dataset represents real interiors and contains a diverse set of…

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…

We propose SceneTex, a novel method for effectively generating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. Unlike previous methods that either iteratively warp 2D views onto a mesh…

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial…

Robots operating in dynamic environments face significant challenges due to the presence of moving agents and displaced objects. Traditional SLAM systems typically assume a static world or treat dynamic as outliers, discarding their…

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…

Traditionally, 3d indoor datasets have generally prioritized scale over ground-truth accuracy in order to obtain improved generalization. However, using these datasets to evaluate dense geometry tasks, such as depth rendering, can be…

Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout…

Scene synthesis is a challenging problem with several industrial applications. Recently, substantial efforts have been directed to synthesize the scene using human motions, room layouts, or spatial graphs as the input. However, few studies…

Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…

We present Action Agent, a two-stage framework that unifies agentic navigation video generation with flow-constrained diffusion control for multi-embodiment robot navigation. In Stage I, a large language model (LLM) acts as an orchestration…

Film set design plays a pivotal role in cinematic storytelling and shaping the visual atmosphere. However, the traditional process depends on expert-driven manual modeling, which is labor-intensive and time-consuming. To address this issue,…

3D scene graphs have empowered robots with semantic understanding for navigation and planning. However, current functional scene graphs primarily focus on static element detection, lacking the actionable kinematic information required for…

Compositional 3D scene synthesis has diverse applications across a spectrum of industries such as robotics, films, and video games, as it closely mirrors the complexity of real-world multi-object environments. Conventional works typically…

Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as…

Scene Classification has been addressed with numerous techniques in computer vision literature. However, with the increasing number of scene classes in datasets in the field, it has become difficult to achieve high accuracy in the context…

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…

Robotic simulation today remains challenging to scale up due to the human efforts required to create diverse simulation tasks and scenes. Simulation-trained policies also face scalability issues as many sim-to-real methods focus on a single…