Recovering detailed interactions between humans/hands and objects is an
appealing yet challenging task. Existing methods typically use template-based
representations to track human/hand and objects in interactions. Despite the
progress, they fail to handle the invisible contact surfaces. In this paper, we
propose Ins-HOI, an end-to-end solution to recover human/hand-object
reconstruction via instance-level implicit reconstruction. To this end, we
introduce an instance-level occupancy field to support simultaneous human/hand
and object representation, and a complementary training strategy to handle the
lack of instance-level ground truths. Such a representation enables learning a
contact prior implicitly from sparse observations. During the complementary
training, we augment the real-captured data with synthesized data by randomly
composing individual scans of humans/hands and objects and intentionally
allowing for penetration. In this way, our network learns to recover individual
shapes as completely as possible from the synthesized data, while being aware
of the contact constraints and overall reasonability based on real-captured
scans. As demonstrated in experiments, our method Ins-HOI can produce
reasonable and realistic non-visible contact surfaces even in cases of
extremely close interaction. To facilitate the research of this task, we
collect a large-scale, high-fidelity 3D scan dataset, including 5.2k
high-quality scans with real-world human-chair and hand-object interactions. We
will release our dataset and source codes. Data examples and the video results
of our method can be found on the project page.

通过实例级隐式重建，我们提出了 Ins-HOI，一种端到端解决方案，用于恢复人与物体之间的详细交互。我们引入了实例级占据场来支持同时表示人 / 手和对象，并使用补充训练策略处理实例级基准缺失的问题。我们的方法 Ins-HOI 能够在极近交互的情况下生成合理和真实的非可见接触表面，并提供了一个大规模高保真度的 3D 扫描数据集用于研究。