PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI

• URL: http://arxiv.org/abs/2404.09465v2
• Date: Wed, 10 Jul 2024 02:43:14 GMT
• Title: PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI
• Authors: Yandan Yang, Baoxiong Jia, Peiyuan Zhi, Siyuan Huang,
• Abstract summary: PhyScene is a method dedicated to generating interactive 3D scenes characterized by realistic layouts, articulated objects, and rich physical interactivity tailored for embodied agents. We demonstrate that PhyScene effectively leverages these guidance functions for physically interactable scene synthesis, outperforming existing state-of-the-art scene synthesis methods by a large margin.
• Score: 38.03745740636854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With recent developments in Embodied Artificial Intelligence (EAI) research, there has been a growing demand for high-quality, large-scale interactive scene generation. While prior methods in scene synthesis have prioritized the naturalness and realism of the generated scenes, the physical plausibility and interactivity of scenes have been largely left unexplored. To address this disparity, we introduce PhyScene, a novel method dedicated to generating interactive 3D scenes characterized by realistic layouts, articulated objects, and rich physical interactivity tailored for embodied agents. Based on a conditional diffusion model for capturing scene layouts, we devise novel physics- and interactivity-based guidance mechanisms that integrate constraints from object collision, room layout, and object reachability. Through extensive experiments, we demonstrate that PhyScene effectively leverages these guidance functions for physically interactable scene synthesis, outperforming existing state-of-the-art scene synthesis methods by a large margin. Our findings suggest that the scenes generated by PhyScene hold considerable potential for facilitating diverse skill acquisition among agents within interactive environments, thereby catalyzing further advancements in embodied AI research. Project website: http://physcene.github.io.

Related papers

• Mixed Diffusion for 3D Indoor Scene Synthesis [55.94569112629208]
  We present MiDiffusion, a novel mixed discrete-continuous diffusion model architecture. We represent a scene layout by a 2D floor plan and a set of objects, each defined by its category, location, size, and orientation. Our experimental results demonstrate that MiDiffusion substantially outperforms state-of-the-art autoregressive and diffusion models in floor-conditioned 3D scene synthesis.
  arXiv  Detail & Related papers  (2024-05-31T17:54:52Z)
• 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)
• Scaling Up Dynamic Human-Scene Interaction Modeling [58.032368564071895]
  TRUMANS is the most comprehensive motion-captured HSI dataset currently available. It intricately captures whole-body human motions and part-level object dynamics. We devise a diffusion-based autoregressive model that efficiently generates HSI sequences of any length.
  arXiv  Detail & Related papers  (2024-03-13T15:45:04Z)
• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion [29.25063155767897]
  This paper addresses a novel task of anticipating 3D human-object interactions (HOIs) Our task is significantly more challenging, as it requires modeling dynamic objects with various shapes, capturing whole-body motion, and ensuring physically valid interactions. Experiments on multiple human-object interaction datasets demonstrate the effectiveness of our method for this task, capable of producing realistic, vivid, and remarkably long-term 3D HOI predictions.
  arXiv  Detail & Related papers  (2023-08-31T17:59:08Z)
• Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning [34.00107506891627]
  We focus on naturally and controllably generating realistic and diverse HSIs from textual descriptions. We propose Narrator, a novel relationship reasoning-based generative approach. Our experiments and perceptual studies show that Narrator can controllably generate diverse interactions and significantly outperform existing works.
  arXiv  Detail & Related papers  (2023-03-16T15:44:15Z)
• Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments [11.87902527509297]
  We present LAMA, Locomotion-Action-MAnipulation, to synthesize natural and plausible long-term human movements in complex indoor environments. Unlike existing methods that require motion data "paired" with scanned 3D scenes for supervision, we formulate the problem as a test-time optimization by using human motion capture data only for synthesis.
  arXiv  Detail & Related papers  (2023-01-09T18:59:16Z)
• Compositional Human-Scene Interaction Synthesis with Semantic Control [16.93177243590465]
  We aim to synthesize humans interacting with a given 3D scene controlled by high-level semantic specifications. We design a novel transformer-based generative model, in which the articulated 3D human body surface points and 3D objects are jointly encoded. Inspired by the compositional nature of interactions that humans can simultaneously interact with multiple objects, we define interaction semantics as the composition of varying numbers of atomic action-object pairs.
  arXiv  Detail & Related papers  (2022-07-26T11:37:44Z)
• Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis [117.15586710830489]
  We focus on the problem of synthesizing diverse scene-aware human motions under the guidance of target action sequences. Based on this factorized scheme, a hierarchical framework is proposed, with each sub-module responsible for modeling one aspect. Experiment results show that the proposed framework remarkably outperforms previous methods in terms of diversity and naturalness.
  arXiv  Detail & Related papers  (2022-05-25T18:20:01Z)
• PLACE: Proximity Learning of Articulation and Contact in 3D Environments [70.50782687884839]
  We propose a novel interaction generation method, named PLACE, which explicitly models the proximity between the human body and the 3D scene around it. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction.
  arXiv  Detail & Related papers  (2020-08-12T21:00:10Z)

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.