GenZI: Zero-Shot 3D Human-Scene Interaction Generation

• URL: http://arxiv.org/abs/2311.17737v1
• Date: Wed, 29 Nov 2023 15:40:11 GMT
• Title: GenZI: Zero-Shot 3D Human-Scene Interaction Generation
• Authors: Lei Li, Angela Dai
• Abstract summary: We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data.
• Score: 39.9039943099911
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene. We then formulate a robust iterative optimization to synthesize the pose and shape of a 3D human model in the scene, guided by consistency with the 2D interaction hypotheses. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data, and allows for flexible control of the 3D interaction synthesis with easy-to-use text prompts. Extensive experiments show that our zero-shot approach has high flexibility and generality, making it applicable to diverse scene types, including both indoor and outdoor environments.

Related papers

• MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling [21.1274747033854]
  Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. Milo is a novel framework which can synthesize character videos with controllable attributes. Milo achieves advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes.
  arXiv  Detail & Related papers  (2024-09-24T15:00:07Z)
• Revisit Human-Scene Interaction via Space Occupancy [55.67657438543008]
  Human-scene Interaction (HSI) generation is a challenging task and crucial for various downstream tasks. In this work, we argue that interaction with a scene is essentially interacting with the space occupancy of the scene from an abstract physical perspective. By treating pure motion sequences as records of humans interacting with invisible scene occupancy, we can aggregate motion-only data into a large-scale paired human-occupancy interaction database.
  arXiv  Detail & Related papers  (2023-12-05T12:03:00Z)
• Synthesizing Diverse Human Motions in 3D Indoor Scenes [16.948649870341782]
  We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human motions and the 3D scenes they interact with. We propose a reinforcement learning-based approach that enables virtual humans to navigate in 3D scenes and interact with objects realistically and autonomously.
  arXiv  Detail & Related papers  (2023-05-21T09:22:24Z)
• HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes [54.61610144668777]
  We present a novel scene-and-language conditioned generative model that can produce 3D human motions in 3D scenes. Our experiments demonstrate that our model generates diverse and semantically consistent human motions in 3D scenes.
  arXiv  Detail & Related papers  (2022-10-18T10:14:11Z)
• 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)
• Human-Aware Object Placement for Visual Environment Reconstruction [63.14733166375534]
  We show that human-scene interactions can be leveraged to improve the 3D reconstruction of a scene from a monocular RGB video. Our key idea is that, as a person moves through a scene and interacts with it, we accumulate HSIs across multiple input images. We show that our scene reconstruction can be used to refine the initial 3D human pose and shape estimation.
  arXiv  Detail & Related papers  (2022-03-07T18:59:02Z)
• Learning Speech-driven 3D Conversational Gestures from Video [106.15628979352738]
  We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. We also contribute a new way to create a large corpus of more than 33 hours of annotated body, hand, and face data from in-the-wild videos of talking people.
  arXiv  Detail & Related papers  (2021-02-13T01:05:39Z)
• 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.