2024/09/12 by Ruining Li, Zhu, Thomas Hanwen, Li, Ruining +2 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.2409.08278
openalex publication_date 2024/09/12 · openalex created_date 2024/10/23 · openalex updated_date 2026/07/28
We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is complicated by the varying categories and geometries of real-world objects and the scarcity of datasets encompassing diverse HOIs. To circumvent the need for extensive data, we leverage text-to-image diffusion models trained on billions of image-caption pairs. We optimize the articulation of a skinned human mesh using Score Distillation Sampling (SDS) gradients obtained from these models, which predict image-space edits. However, directly backpropagating image-space gradients into complex articulation parameters is ineffective due to the local nature of such gradients. To overcome this, we introduce a dual implicit-explicit representation of a skinned mesh, combining (implicit) neural radiance fields (NeRFs) with (explicit) skeleton-driven mesh articulation. During optimization, we transition between implicit and explicit forms, grounding the NeRF generation while refining the mesh articulation. We validate our approach through extensive experiments, demonstrating its effectiveness in generating realistic HOIs.