SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

• URL: http://arxiv.org/abs/2411.19921v2
• Date: Sun, 16 Mar 2025 04:09:27 GMT
• Title: SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
• Authors: Wenjia Wang, Liang Pan, Zhiyang Dou, Jidong Mei, Zhouyingcheng Liao, Yuke Lou, Yifan Wu, Lei Yang, Jingbo Wang, Taku Komura,
• Abstract summary: We introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy.<n>Specifically, we employ Large Language Models with Retrieval-Augmented Generation to generate coherent and diverse long-form scripts.<n>A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues.
• Score: 38.96874874208242
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form scripts, providing a rich foundation for motion planning. A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues, simultaneously perceiving environmental geometries and accomplishing task goals. By integrating the retrieval-augmented script generation with the multi-condition controller, our approach provides a unified solution for generating stylized HSI motions. We further introduce a comprehensive planning dataset produced by RAG and a stylized motion dataset featuring diverse locomotions and interactions. Extensive experiments demonstrate SIMS's effectiveness in executing various tasks and generalizing across different scenarios, significantly outperforming previous methods.

Related papers

• GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration [20.988801611785522]
  We propose GenMAC, an iterative, multi-agent framework that enables compositional text-to-video generation. The collaborative workflow includes three stages: Design, Generation, and Redesign. To tackle diverse scenarios of compositional text-to-video generation, we design a self-routing mechanism to adaptively select the proper correction agent from a collection of correction agents each specialized for one scenario.
  arXiv  Detail & Related papers  (2024-12-05T18:56:05Z)
• Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation [16.244250979166214]
  Generalizable Planning-Guided Diffusion Policy Learning (GLIDE) is an approach that learns to solve contact-rich bimanual manipulation tasks. We propose a set of essential design options in feature extraction, task representation, action prediction, and data augmentation. Our approach can enable a bimanual robotic system to effectively manipulate objects of diverse geometries, dimensions, and physical properties.
  arXiv  Detail & Related papers  (2024-12-03T18:51:39Z)
• Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies. Our findings are synthesized in Flex (Fly-lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors. We demonstrate the effectiveness of this approach on quadrotor fly-to-target tasks, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)
• Towards Multi-Task Multi-Modal Models: A Video Generative Perspective [5.495245220300184]
  This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Our scalable visual token representation proves beneficial across generation, compression, and understanding tasks.
  arXiv  Detail & Related papers  (2024-05-26T23:56:45Z)
• Generating Human Interaction Motions in Scenes with Text Control [66.74298145999909]
  We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model. To facilitate training, we embed annotated navigation and interaction motions within scenes.
  arXiv  Detail & Related papers  (2024-04-16T16:04:38Z)
• MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments [82.67236400004826]
  We introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions. MEM module enables MEIA to generate executable action plans based on diverse requirements and the robot's capabilities.
  arXiv  Detail & Related papers  (2024-02-01T02:43:20Z)
• DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent) [73.10899129264375]
  This paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. We extensively evaluate DoraemonGPT's effectiveness on three benchmarks and several in-the-wild scenarios.
  arXiv  Detail & Related papers  (2024-01-16T14:33:09Z)
• VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools [44.78291853329394]
  textbfVidCoM is a fast adaptive framework that leverages Large Language Models (LLMs) to reason about videos using lightweight visual tools. An InsOVER algorithm locates the corresponding video events based on an efficient Hungarian matching between decompositions of linguistic instructions and video events.
  arXiv  Detail & Related papers  (2023-10-16T17:05:56Z)
• Unified Human-Scene Interaction via Prompted Chain-of-Contacts [61.87652569413429]
  Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands.
  arXiv  Detail & Related papers  (2023-09-14T17:59:49Z)
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models [38.503337052122234]
  Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation. We aim to synthesize robot trajectories for a variety of manipulation tasks given an open-set of instructions and an open-set of objects. We demonstrate how the proposed framework can benefit from online experiences by efficiently learning a dynamics model for scenes that involve contact-rich interactions.
  arXiv  Detail & Related papers  (2023-07-12T07:40:48Z)
• A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot [67.00455874279383]
  We propose verbalizing long videos to generate descriptions in natural language, then performing video-understanding tasks on the generated story as opposed to the original video. Our method, despite being zero-shot, achieves significantly better results than supervised baselines for video understanding. To alleviate a lack of story understanding benchmarks, we publicly release the first dataset on a crucial task in computational social science on persuasion strategy identification.
  arXiv  Detail & Related papers  (2023-05-16T19:13:11Z)
• Synthesizing Physical Character-Scene Interactions [64.26035523518846]
  It is necessary to synthesize such interactions between virtual characters and their surroundings. We present a system that uses adversarial imitation learning and reinforcement learning to train physically-simulated characters. Our approach takes physics-based character motion generation a step closer to broad applicability.
  arXiv  Detail & Related papers  (2023-02-02T05:21:32Z)
• Learning Action-Effect Dynamics from Pairs of Scene-graphs [50.72283841720014]
  We propose a novel method that leverages scene-graph representation of images to reason about the effects of actions described in natural language. Our proposed approach is effective in terms of performance, data efficiency, and generalization capability compared to existing models.
  arXiv  Detail & Related papers  (2022-12-07T03:36:37Z)
• DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation [71.87682778102236]
  We propose a novel Dynamical Semantic Evolution GAN (DSE-GAN) to re-compose each stage's text features under a novel single adversarial multi-stage architecture. DSE-GAN achieves 7.48% and 37.8% relative FID improvement on two widely used benchmarks.
  arXiv  Detail & Related papers  (2022-09-03T06:13:26Z)
• iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes [54.04456391489063]
  iGibson is a novel simulation environment to develop robotic solutions for interactive tasks in large-scale realistic scenes. Our environment contains fifteen fully interactive home-sized scenes populated with rigid and articulated objects. iGibson features enable the generalization of navigation agents, and that the human-iGibson interface and integrated motion planners facilitate efficient imitation learning of simple human demonstrated behaviors.
  arXiv  Detail & Related papers  (2020-12-05T02:14:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.