2026-10-02 東京科学大学
図1. 12台の同期カメラ、一人称映像、音声、3D姿勢推定を組み合わせたInerPet4Dの概要（下段）。
＜関連情報＞
InterPet4D：ペットの動きを生成するためのマルチモーダル4D人間・ペット相互作用データセット InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation
Yichen Peng, Jyun-Ting Song, Chen-Chieh Liao, Kris Kitani, Hideki Koike, Erwin Wu
The 19th European Conference on Computer Vision
arXiv Submitted on 11 Jul 2026
DOI:https://doi.org/10.48550/arXiv.2607.10287
Abstract
Human-pet interaction estimation and generation remain underexplored due to the absence of a high-quality large-scale dataset. We present InterPet4D, the first multimodal dataset capturing natural interactions between humans and dogs. Using a synchronized multi-view capture system, we record human-dog obedience tasks and provide annotations for both humans and dogs, including multi-view and egocentric videos, segmentations, 2D and 3D keypoints, meshes, and audio tracks. InterPet4D consists of 6.8 million frames collected from 13 dogs of 11 breeds interacting with 23 human participants. We further introduce the InterPetMoGen framework for human-pet interaction motion generation. Our proposed model achieves an FID score of 11.21 and substantially outperforms the Seq2Seq and DiT baselines, demonstrating the effectiveness of InterPet4D for modeling realistic human-pet interactions.
