Saved in:
Bibliographic Details
Main Authors: Zhong, Yu, Zhang, Rui, Zhang, Zihao, Wang, Shuo, Fang, Chuan, Zhang, Xishan, Guo, Jiaming, Peng, Shaohui, Huang, Di, Yan, Yanyang, Hu, Xing, Guo, Qi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.06413
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908420548853760
author Zhong, Yu
Zhang, Rui
Zhang, Zihao
Wang, Shuo
Fang, Chuan
Zhang, Xishan
Guo, Jiaming
Peng, Shaohui
Huang, Di
Yan, Yanyang
Hu, Xing
Guo, Qi
author_facet Zhong, Yu
Zhang, Rui
Zhang, Zihao
Wang, Shuo
Fang, Chuan
Zhang, Xishan
Guo, Jiaming
Peng, Shaohui
Huang, Di
Yan, Yanyang
Hu, Xing
Guo, Qi
contents Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency, aimed at enhancing the generalization of agents to novel environments. Roughly, our framework consists of two stages, the trajectory stage which leverages a point-cloud based technique to ensure spatial coherency among viewpoints, and the viewpoint stage which adopts a novel angle synthesis method to guarantee spatial and wraparound consistency within the entire observation. By accurately predicting viewpoint changes with 3D knowledge, our approach maintains the world-consistency during the generation procedure. Experiments on a wide range of datasets verify the effectiveness of our method, demonstrating that our data augmentation strategy enables agents to achieve new state-of-the-art results on all navigation tasks, and is capable of enhancing the VLN agents' generalization ability to unseen environments.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06413
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle World-Consistent Data Generation for Vision-and-Language Navigation
Zhong, Yu
Zhang, Rui
Zhang, Zihao
Wang, Shuo
Fang, Chuan
Zhang, Xishan
Guo, Jiaming
Peng, Shaohui
Huang, Di
Yan, Yanyang
Hu, Xing
Guo, Qi
Computer Vision and Pattern Recognition
Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency, aimed at enhancing the generalization of agents to novel environments. Roughly, our framework consists of two stages, the trajectory stage which leverages a point-cloud based technique to ensure spatial coherency among viewpoints, and the viewpoint stage which adopts a novel angle synthesis method to guarantee spatial and wraparound consistency within the entire observation. By accurately predicting viewpoint changes with 3D knowledge, our approach maintains the world-consistency during the generation procedure. Experiments on a wide range of datasets verify the effectiveness of our method, demonstrating that our data augmentation strategy enables agents to achieve new state-of-the-art results on all navigation tasks, and is capable of enhancing the VLN agents' generalization ability to unseen environments.
title World-Consistent Data Generation for Vision-and-Language Navigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06413