GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
ICLR 2024(2024)
摘要
In this work, we tackle the challenging problem of denoising hand-object
interactions (HOI). Given an erroneous interaction sequence, the objective is
to refine the incorrect hand trajectory to remove interaction artifacts for a
perceptually realistic sequence. This challenge involves intricate interaction
noise, including unnatural hand poses and incorrect hand-object relations,
alongside the necessity for robust generalization to new interactions and
diverse noise patterns. We tackle those challenges through a novel approach,
GeneOH Diffusion, incorporating two key designs: an innovative contact-centric
HOI representation named GeneOH and a new domain-generalizable denoising
scheme. The contact-centric representation GeneOH informatively parameterizes
the HOI process, facilitating enhanced generalization across various HOI
scenarios. The new denoising scheme consists of a canonical denoising model
trained to project noisy data samples from a whitened noise space to a clean
data manifold and a "denoising via diffusion" strategy which can handle input
trajectories with various noise patterns by first diffusing them to align with
the whitened noise space and cleaning via the canonical denoiser. Extensive
experiments on four benchmarks with significant domain variations demonstrate
the superior effectiveness of our method. GeneOH Diffusion also shows promise
for various downstream applications. Project website:
https://meowuu7.github.io/GeneOH-Diffusion/.
更多查看译文
关键词
motion refinement,hand-object interaction,inverse problem,generative prior
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要