Mar 22, 2024 · In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner.
InterFusion is a two-stage framework that transforms textual descriptions into detailed 3D human-object interactions.
Inter-. Fusion involves human pose estimations derived from text as geometric priors, which simplifies the text-to-3D conversion process and introduces.
InterFusion can generate diverse 3D scenes of human-object interaction (3D HOI) given texts. [Project Page] • [arXiv] • [PDF]
InterFusion involves human pose estimations derived from text as geometric priors, which simplifies the text-to-3D conversion process and introduces additional ...
InterFusion is a two-stage framework that transforms textual descriptions into detailed 3D human-object interactions.
People also search for
Nov 27, 2024 · InterFusion involves human pose estimations derived from text as geometric priors, which simplifies the text-to-3D conversion process and ...
HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using ...
neu-vi.github.io › HOI-Diff
HOI-Diff can generate realistic motions for 3D human-object interactions given a text prompt and object geometry.
Oct 15, 2024 · HOI-Diff is a diffusion-based model for generating realistic 3D human-object interactions (HOIs) from textual descriptions.
View recent discussion. Abstract: In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a ...
People also ask
What is human-object interaction?
What is a human-object?