cs.CVNov 15, 2026

SGIP: Learning Scene-Grounded Interaction Priors for Scene-Aware Human Motion Prediction

Authors: Donghyeon Soon, Jiil Yoon, Hyeondong Kim, Daehee Park

Organizations: DGIST · UNIVA

Abstract

Human motion prediction (HMP) aims to forecast future movement from an observed motion sequence, and recent methods have incorporated 3D scene geometry and object semantics to improve long-term plausibility. However, the destination of future motion remains ambiguous in cluttered scenes: the same observed motion can lead to different interaction targets or navigation modes. Existing methods either handle this ambiguity implicitly or rely on auxiliary signals like gaze that are hard to obtain in practice. To address this, we propose SGIP, which explicitly predicts where in the scene future motion will be grounded across both objects and open navigation regions, and uses it to condition future trajectory and full-body pose prediction. This scene-grounded interaction prior is learned via intent distillation: at training time only, a teacher model scores candidate scene regions by combining an LLM prompted with a textual description of the person's intent with geometric motion-scene features. A student model learns to reproduce these scores from only the observed motion and 3D scene, making intent and LLM unnecessary at test time. Across multiple benchmark datasets, SGIP outperforms prior scene-aware baselines on both trajectory and pose accuracy in a realistic deployment setting where neither gaze nor intent is available at inference, demonstrating the effectiveness of the proposed framework. The project page is available at https://sgip2026.github.io.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues

    Nov 10, 2026Xin Zhao, Pengzhan Zhou, Ziyi Li +3Human Motion PredictionHuman Motion Generation

  2. Ego-Human Motion Prediction with 3D-Aware LLM

    Jul 8, 2026Yujin Bae, Jaewoo Jeong, Hyeonseong Kim +1Egocentric Video UnderstandingHuman Motion Prediction

  3. Comparing Utility of Inertial, Occupancy, Semantic, and Intent Information in Human Motion Prediction During Daily Tasks

    Sep 29, 2026Max Burns, Maisha Khanum, Monroe Kennedy +1Human Motion Prediction