g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zihan, Lee, Gim Hee
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909405319004160
author Wang, Zihan
Lee, Gim Hee
author_facet Wang, Zihan
Lee, Gim Hee
contents We introduce Generalizable 3D-Language Feature Fields (g3D-LF), a 3D representation model pre-trained on large-scale 3D-language dataset for embodied tasks. Our g3D-LF processes posed RGB-D images from agents to encode feature fields for: 1) Novel view representation predictions from any position in the 3D scene; 2) Generations of BEV maps centered on the agent; 3) Querying targets using multi-granularity language within the above-mentioned representations. Our representation can be generalized to unseen environments, enabling real-time construction and dynamic updates. By volume rendering latent features along sampled rays and integrating semantic and spatial relationships through multiscale encoders, our g3D-LF produces representations at different scales and perspectives, aligned with multi-granularity language, via multi-level contrastive learning. Furthermore, we prepare a large-scale 3D-language dataset to align the representations of the feature fields with language. Extensive experiments on Vision-and-Language Navigation under both Panorama and Monocular settings, Zero-shot Object Navigation, and Situated Question Answering tasks highlight the significant advantages and effectiveness of our g3D-LF for embodied tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17030
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
Wang, Zihan
Lee, Gim Hee
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
We introduce Generalizable 3D-Language Feature Fields (g3D-LF), a 3D representation model pre-trained on large-scale 3D-language dataset for embodied tasks. Our g3D-LF processes posed RGB-D images from agents to encode feature fields for: 1) Novel view representation predictions from any position in the 3D scene; 2) Generations of BEV maps centered on the agent; 3) Querying targets using multi-granularity language within the above-mentioned representations. Our representation can be generalized to unseen environments, enabling real-time construction and dynamic updates. By volume rendering latent features along sampled rays and integrating semantic and spatial relationships through multiscale encoders, our g3D-LF produces representations at different scales and perspectives, aligned with multi-granularity language, via multi-level contrastive learning. Furthermore, we prepare a large-scale 3D-language dataset to align the representations of the feature fields with language. Extensive experiments on Vision-and-Language Navigation under both Panorama and Monocular settings, Zero-shot Object Navigation, and Situated Question Answering tasks highlight the significant advantages and effectiveness of our g3D-LF for embodied tasks.
title g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2411.17030