Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Endres, Jannik, Hahn, Oliver, Corbière, Charles, Schaub-Meyer, Simone, Roth, Stefan, Alahi, Alexandre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915580660940800
author Endres, Jannik
Hahn, Oliver
Corbière, Charles
Schaub-Meyer, Simone
Roth, Stefan
Alahi, Alexandre
author_facet Endres, Jannik
Hahn, Oliver
Corbière, Charles
Schaub-Meyer, Simone
Roth, Stefan
Alahi, Alexandre
contents Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps without relying on expensive active sensing. However, existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments, depth ranges, and lighting conditions, due to the scarcity of real-world data. We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation within an iterative optimization-based stereo matching architecture. We introduce a dedicated two-stage training strategy to utilize the relative monocular depth features for our omnidirectional stereo matching before scale-invariant fine-tuning. DFI-OmniStereo achieves state-of-the-art results on the real-world Helvipad dataset, reducing disparity MAE by approximately 16% compared to the previous best omnidirectional stereo method.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23502
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
Endres, Jannik
Hahn, Oliver
Corbière, Charles
Schaub-Meyer, Simone
Roth, Stefan
Alahi, Alexandre
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps without relying on expensive active sensing. However, existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments, depth ranges, and lighting conditions, due to the scarcity of real-world data. We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation within an iterative optimization-based stereo matching architecture. We introduce a dedicated two-stage training strategy to utilize the relative monocular depth features for our omnidirectional stereo matching before scale-invariant fine-tuning. DFI-OmniStereo achieves state-of-the-art results on the real-world Helvipad dataset, reducing disparity MAE by approximately 16% compared to the previous best omnidirectional stereo method.
title Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2503.23502