SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

• URL: http://arxiv.org/abs/2510.13044v1
• Date: Tue, 14 Oct 2025 23:42:10 GMT
• Title: SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion
• Authors: Jungbin Cho, Minsu Kim, Jisoo Kim, Ce Zheng, Laszlo A. Jeni, Ming-Hsuan Yang, Youngjae Yu, Seonjoo Kim,
• Abstract summary: We introduce SceneAdapt, a framework that injects scene awareness into text-conditioned motion models.<n>Key idea is to use motion inbetweening, learnable without text, as a proxy task to bridge two distinct datasets.<n>Results show that SceneAdapt effectively injects scene awareness into text-to-motion models.
• Score: 74.70024991949269
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene. However, existing motion generation approaches address either motion semantics or scene-awareness in isolation, since constructing large-scale datasets with both rich text--motion coverage and precise scene interactions is extremely challenging. In this work, we introduce SceneAdapt, a framework that injects scene awareness into text-conditioned motion models by leveraging disjoint scene--motion and text--motion datasets through two adaptation stages: inbetweening and scene-aware inbetweening. The key idea is to use motion inbetweening, learnable without text, as a proxy task to bridge two distinct datasets and thereby inject scene-awareness to text-to-motion models. In the first stage, we introduce keyframing layers that modulate motion latents for inbetweening while preserving the latent manifold. In the second stage, we add a scene-conditioning layer that injects scene geometry by adaptively querying local context through cross-attention. Experimental results show that SceneAdapt effectively injects scene awareness into text-to-motion models, and we further analyze the mechanisms through which this awareness emerges. Code and models will be released.

Related papers

• SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control [36.22743674288336]
  SCENIC is a diffusion model designed to generate human motion that adapts to dynamic terrains within virtual scenes.<n>Our system achieves seamless transitions between different motion styles while maintaining scene constraints.<n>Our code, dataset, and models will be released at urlhttps://virtualhumans.mpi-inf.mpg.de/scenic/.
  arXiv  Detail & Related papers  (2024-12-20T08:25:15Z)
• Generating Human Motion in 3D Scenes from Text Descriptions [60.04976442328767]
  This paper focuses on the task of generating human motions in 3D indoor scenes given text descriptions of the human-scene interactions. We propose a new approach that decomposes the complex problem into two more manageable sub-problems. For language grounding of the target object, we leverage the power of large language models; for motion generation, we design an object-centric scene representation.
  arXiv  Detail & Related papers  (2024-05-13T14:30:12Z)
• 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)
• GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts [48.28000728061778]
  We propose a method that integrates an open vocabulary scene encoder into the architecture, establishing a robust connection between text and scene. Our methodology achieves up to a 30% reduction in the goal object distance metric compared to the prior state-of-the-art baseline model.
  arXiv  Detail & Related papers  (2024-04-08T18:24:12Z)
• Animate Your Motion: Turning Still Images into Dynamic Videos [58.63109848837741]
  We introduce Scene and Motion Conditional Diffusion (SMCD), a novel methodology for managing multimodal inputs. SMCD incorporates a recognized motion conditioning module and investigates various approaches to integrate scene conditions. Our design significantly enhances video quality, motion precision, and semantic coherence.
  arXiv  Detail & Related papers  (2024-03-15T10:36:24Z)
• Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer [27.278989809466392]
  We present a new method for text-driven motion transfer - synthesizing a video that complies with an input text prompt describing the target objects and scene. We leverage a pre-trained and fixed text-to-video diffusion model, which provides us with generative and motion priors.
  arXiv  Detail & Related papers  (2023-11-28T18:03:27Z)
• 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)

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.