Tag
MAMHOI 通过动作可供性（affordances）对场景感知的人-物交互生成进行解耦，利用场景条件模型预测可供性，再由可供性条件生成模型合成协调的人-物运动，从而无需配对的人-物-场景训练数据即可生成更符合场景几何、减少穿透的交互运动。
COSMI 是一项关于多物体人机物交互合成的研究，提出了由单物体捕捉合成的 222k 序列/275 小时大规模数据集，以及一个 3000 万参数的文本到交互扩散 Transformer，可生成 1 到 5 个物体的交互并在未见物体与未见交互组合上泛化。
PAMI 提出一种 Part-Anchored Motion 框架，通过身体部位锚点投票机制和粗到细的生成层级（PamiGen 与 PamiRefiner）实现文本条件下的全身人-物交互生成，在 InterAct 数据集上较此前 SOTA 提升 14.5% 的接触召回率。
HOI-Retarget introduces a contact-centric retargeting method for transferring human-object interactions to humanoid robots, enabling large-scale motion data generation from single demonstrations and monocular video contacts.
HOMIE is a framework for human-object centric video personalization that integrates MLLM features to improve subject fidelity and interaction patterns, achieving state-of-the-art performance.
PhyGenHOI is a novel framework that generates physically accurate 4D human-object interactions by coupling motion diffusion models with material point method simulations using 3D Gaussian representations.
DeVI introduces a framework that turns text-conditioned synthetic videos into physically plausible dexterous robot control via a hybrid 3D-2D tracking reward, enabling zero-shot generalization to unseen objects.
CoInteract introduces an end-to-end Diffusion Transformer framework that jointly models RGB appearance and HOI geometry to generate physically-plausible human-object interaction videos with stable hands/faces and zero inference overhead.
OneHOI is a unified diffusion transformer framework that consolidates human-object interaction (HOI) generation and editing into a single conditional denoising process using relational modeling and structured attention mechanisms. The approach achieves state-of-the-art results across both HOI generation and editing tasks with support for multiple control modalities.