English

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World

Computer Vision and Pattern Recognition 2025-08-06 v1 Robotics

Abstract

We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first method of its kind to enable probabilistic pose and shape estimation. OmniShape is based on the key insight that shape completion can be decoupled into two multi-modal distributions: one capturing how measurements project into a normalized object reference frame defined by the dataset and the other modelling a prior over object geometries represented as triplanar neural fields. By training separate conditional diffusion models for these two distributions, we enable sampling multiple hypotheses from the joint pose and shape distribution. OmniShape demonstrates compelling performance on challenging real world datasets. Project website: https://tri-ml.github.io/omnishape

Keywords

Cite

@article{arxiv.2508.03669,
  title  = {OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World},
  author = {Katherine Liu and Sergey Zakharov and Dian Chen and Takuya Ikeda and Greg Shakhnarovich and Adrien Gaidon and Rares Ambrus},
  journal= {arXiv preprint arXiv:2508.03669},
  year   = {2025}
}

Comments

8 pages, 5 figures. This version has typo fixes on top of the version published at ICRA 2025

R2 v1 2026-07-01T04:35:36.468Z