Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Yinxuan, Gao, Chengmin, Li, Bin, Xue, Xiangyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913569629536256
author Huang, Yinxuan
Gao, Chengmin
Li, Bin
Xue, Xiangyang
author_facet Huang, Yinxuan
Gao, Chengmin
Li, Bin
Xue, Xiangyang
contents Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random or sequential viewpoint selection strategies. While applicable across various scenes, these strategies may not always be ideal, as certain scenes could benefit more from specific viewpoints. To address this limitation, we propose a novel active viewpoint selection strategy. This strategy predicts images from unknown viewpoints based on information from observation images for each scene. It then compares the object-centric representations extracted from both viewpoints and selects the unknown viewpoint with the largest disparity, indicating the greatest gain in information, as the next observation viewpoint. Through experiments on various datasets, we demonstrate the effectiveness of our active viewpoint selection strategy, significantly enhancing segmentation and reconstruction performance compared to random viewpoint selection. Moreover, our method can accurately predict images from unknown viewpoints.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00402
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Huang, Yinxuan
Gao, Chengmin
Li, Bin
Xue, Xiangyang
Computer Vision and Pattern Recognition
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random or sequential viewpoint selection strategies. While applicable across various scenes, these strategies may not always be ideal, as certain scenes could benefit more from specific viewpoints. To address this limitation, we propose a novel active viewpoint selection strategy. This strategy predicts images from unknown viewpoints based on information from observation images for each scene. It then compares the object-centric representations extracted from both viewpoints and selects the unknown viewpoint with the largest disparity, indicating the greatest gain in information, as the next observation viewpoint. Through experiments on various datasets, we demonstrate the effectiveness of our active viewpoint selection strategy, significantly enhancing segmentation and reconstruction performance compared to random viewpoint selection. Moreover, our method can accurately predict images from unknown viewpoints.
title Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.00402