Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pulling, Conner, Tan, Je Hon, Hu, Yaoyu, Scherer, Sebastian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909196178423808
author Pulling, Conner
Tan, Je Hon
Hu, Yaoyu
Scherer, Sebastian
author_facet Pulling, Conner
Tan, Je Hon
Hu, Yaoyu
Scherer, Sebastian
contents Multi-view stereo omnidirectional distance estimation usually needs to build a cost volume with many hypothetical distance candidates. The cost volume building process is often computationally heavy considering the limited resources a mobile robot has. We propose a new geometry-informed way of distance candidates selection method which enables the use of a very small number of candidates and reduces the computational cost. We demonstrate the use of the geometry-informed candidates in a set of model variants. We find that by adjusting the candidates during robot deployment, our geometry-informed distance candidates also improve a pre-trained model's accuracy if the extrinsics or the number of cameras changes. Without any re-training or fine-tuning, our models outperform models trained with evenly distributed distance candidates. Models are also released as hardware-accelerated versions with a new dedicated large-scale dataset. The project page, code, and dataset can be found at https://theairlab.org/gicandidates/ .
format Preprint
id arxiv_https___arxiv_org_abs_2405_05355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images
Pulling, Conner
Tan, Je Hon
Hu, Yaoyu
Scherer, Sebastian
Computer Vision and Pattern Recognition
Robotics
Multi-view stereo omnidirectional distance estimation usually needs to build a cost volume with many hypothetical distance candidates. The cost volume building process is often computationally heavy considering the limited resources a mobile robot has. We propose a new geometry-informed way of distance candidates selection method which enables the use of a very small number of candidates and reduces the computational cost. We demonstrate the use of the geometry-informed candidates in a set of model variants. We find that by adjusting the candidates during robot deployment, our geometry-informed distance candidates also improve a pre-trained model's accuracy if the extrinsics or the number of cameras changes. Without any re-training or fine-tuning, our models outperform models trained with evenly distributed distance candidates. Models are also released as hardware-accelerated versions with a new dedicated large-scale dataset. The project page, code, and dataset can be found at https://theairlab.org/gicandidates/ .
title Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2405.05355