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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Katherine, Zakharov, Sergey, Chen, Dian, Ikeda, Takuya, Shakhnarovich, Greg, Gaidon, Adrien, Ambrus, Rares
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915428992811008
author Liu, Katherine
Zakharov, Sergey
Chen, Dian
Ikeda, Takuya
Shakhnarovich, Greg
Gaidon, Adrien
Ambrus, Rares
author_facet Liu, Katherine
Zakharov, Sergey
Chen, Dian
Ikeda, Takuya
Shakhnarovich, Greg
Gaidon, Adrien
Ambrus, Rares
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2508_03669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
Liu, Katherine
Zakharov, Sergey
Chen, Dian
Ikeda, Takuya
Shakhnarovich, Greg
Gaidon, Adrien
Ambrus, Rares
Computer Vision and Pattern Recognition
Robotics
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
title OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2508.03669