Search papers, labs, and topics across Lattice.
This paper introduces MILO, a novel framework that utilizes Large Reconstruction Models (LRMs) to accurately reconstruct 3D human-object interactions from a single image, addressing challenges like depth ambiguities and occlusions. By leveraging the geometric scaffolding provided by LRMs, the authors simplify the reconstruction process into a segmentation task, fitting parametric models to the human and object components. MILO demonstrates superior reconstruction accuracy compared to existing methods across various benchmarks and interaction scenarios, highlighting its effectiveness in 3D computer vision applications.
MILO redefines 3D human-object interaction reconstruction by leveraging Large Reconstruction Models, achieving unprecedented accuracy from just a single image.
Estimation of Human-Object Interactions in 3D (3D HOI) is a fundamental problem in 3D computer vision with applications in AR/VR, robotics, and embodied AI. However, reconstructing these interactions in 3D remains challenging due to depth ambiguities, occlusions, and object shape variability. Existing approaches are primarily concerned with reprojection and contact constraints, fitting parametric human models and object templates to 2D images. In this paper, we explore a different avenue. We present MILO, a framework that leverages the visual capabilities of Large Reconstruction Models (LRMs) to recover detailed 3D human-object interactions from a single image. Our key observation is that LRMs provide a powerful geometric scaffold that preserves relative human-object arrangement and proximity cues. This significantly simplifies the reconstruction procedure, reframing the problem as interpreting the LRM mesh: we segment it into human and object components, fit a parametric body model to the human part, and optionally align an object template to the object part (if such a template is available). MILO achieves strong reconstruction accuracy and outperforms existing baselines across multiple benchmarks and interaction scenarios. Our code is available at https://ac5113.github.io/MILO.
