FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Bowen, Yang, Wei, Kautz, Jan, Birchfield, Stan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913285744361472
author Wen, Bowen
Yang, Wei
Kautz, Jan
Birchfield, Stan
author_facet Wen, Bowen
Yang, Wei
Kautz, Jan
Birchfield, Stan
contents We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning, as long as its CAD model is given, or a small number of reference images are captured. We bridge the gap between these two setups with a neural implicit representation that allows for effective novel view synthesis, keeping the downstream pose estimation modules invariant under the same unified framework. Strong generalizability is achieved via large-scale synthetic training, aided by a large language model (LLM), a novel transformer-based architecture, and contrastive learning formulation. Extensive evaluation on multiple public datasets involving challenging scenarios and objects indicate our unified approach outperforms existing methods specialized for each task by a large margin. In addition, it even achieves comparable results to instance-level methods despite the reduced assumptions. Project page: https://nvlabs.github.io/FoundationPose/
format Preprint
id arxiv_https___arxiv_org_abs_2312_08344
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Wen, Bowen
Yang, Wei
Kautz, Jan
Birchfield, Stan
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning, as long as its CAD model is given, or a small number of reference images are captured. We bridge the gap between these two setups with a neural implicit representation that allows for effective novel view synthesis, keeping the downstream pose estimation modules invariant under the same unified framework. Strong generalizability is achieved via large-scale synthetic training, aided by a large language model (LLM), a novel transformer-based architecture, and contrastive learning formulation. Extensive evaluation on multiple public datasets involving challenging scenarios and objects indicate our unified approach outperforms existing methods specialized for each task by a large margin. In addition, it even achieves comparable results to instance-level methods despite the reduced assumptions. Project page: https://nvlabs.github.io/FoundationPose/
title FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2312.08344