PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Shutong, Wang, Ruiyu, Chen, Kuangyi, Pokorny, Florian T.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910721775763456
author Jin, Shutong
Wang, Ruiyu
Chen, Kuangyi
Pokorny, Florian T.
author_facet Jin, Shutong
Wang, Ruiyu
Chen, Kuangyi
Pokorny, Florian T.
contents Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative models such as Stable Diffusion can aid by generating natural scenes as goals. To facilitate robot execution, object-level representations must be extracted to match the real scenes with the generated goals and to calculate object pose transformations. Current methods typically use a multi-step design that involves separate models for generation, segmentation, and feature encoding, which can lead to a low success rate due to error accumulation. Furthermore, they lack control over the viewing perspectives of the generated goals, restricting the tasks to 3-DoF settings. In this paper, we propose PACA, a zero-shot pipeline for scene rearrangement that leverages perspective-aware cross-attention representation derived from Stable Diffusion. Specifically, we develop a representation that integrates generation, segmentation, and feature encoding into a single step to produce object-level representations. Additionally, we introduce perspective control, thus enabling the matching of 6-DoF camera views and extending past approaches that were limited to 3-DoF top-down views. The efficacy of our method is demonstrated through its zero-shot performance in real robot experiments across various scenes, achieving an average matching accuracy and execution success rate of 87% and 67%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22059
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement
Jin, Shutong
Wang, Ruiyu
Chen, Kuangyi
Pokorny, Florian T.
Robotics
Computer Vision and Pattern Recognition
Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative models such as Stable Diffusion can aid by generating natural scenes as goals. To facilitate robot execution, object-level representations must be extracted to match the real scenes with the generated goals and to calculate object pose transformations. Current methods typically use a multi-step design that involves separate models for generation, segmentation, and feature encoding, which can lead to a low success rate due to error accumulation. Furthermore, they lack control over the viewing perspectives of the generated goals, restricting the tasks to 3-DoF settings. In this paper, we propose PACA, a zero-shot pipeline for scene rearrangement that leverages perspective-aware cross-attention representation derived from Stable Diffusion. Specifically, we develop a representation that integrates generation, segmentation, and feature encoding into a single step to produce object-level representations. Additionally, we introduce perspective control, thus enabling the matching of 6-DoF camera views and extending past approaches that were limited to 3-DoF top-down views. The efficacy of our method is demonstrated through its zero-shot performance in real robot experiments across various scenes, achieving an average matching accuracy and execution success rate of 87% and 67%, respectively.
title PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22059