An Image-like Diffusion Method for Human-Object Interaction Detection
Journal:
arXiv
Published Date:
Mar 23, 2025
Abstract
Human-object interaction (HOI) detection often faces high levels of ambiguity
and indeterminacy, as the same interaction can appear vastly different across
different human-object pairs. Additionally, the indeterminacy can be further
exacerbated by issues such as occlusions and cluttered backgrounds. To handle
such a challenging task, in this work, we begin with a key observation: the
output of HOI detection for each human-object pair can be recast as an image.
Thus, inspired by the strong image generation capabilities of image diffusion
models, we propose a new framework, HOI-IDiff. In HOI-IDiff, we tackle HOI
detection from a novel perspective, using an Image-like Diffusion process to
generate HOI detection outputs as images. Furthermore, recognizing that our
recast images differ in certain properties from natural images, we enhance our
framework with a customized HOI diffusion process and a slice patchification
model architecture, which are specifically tailored to generate our recast
``HOI images''. Extensive experiments demonstrate the efficacy of our
framework.
