Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network
via Disparity Plane Sweep
- URL: http://arxiv.org/abs/2401.12001v2
- Date: Tue, 23 Jan 2024 03:19:12 GMT
- Title: Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network
via Disparity Plane Sweep
- Authors: Jae Young Lee, Woonghyun Ka, Jaehyun Choi, Junmo Kim
- Abstract summary: The proposed stereo-confidence method is built upon the idea that any shift in a stereo-image pair should be updated in a corresponding amount shift in the disparity map.
By comparing the desirable and predicted disparity profiles, we can quantify the level of matching ambiguity between left and right images for confidence measurement.
- Score: 31.261772846687297
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a novel stereo-confidence that can be measured externally to
various stereo-matching networks, offering an alternative input modality choice
of the cost volume for learning-based approaches, especially in safety-critical
systems. Grounded in the foundational concepts of disparity definition and the
disparity plane sweep, the proposed stereo-confidence method is built upon the
idea that any shift in a stereo-image pair should be updated in a corresponding
amount shift in the disparity map. Based on this idea, the proposed
stereo-confidence method can be summarized in three folds. 1) Using the
disparity plane sweep, multiple disparity maps can be obtained and treated as a
3-D volume (predicted disparity volume), like the cost volume is constructed.
2) One of these disparity maps serves as an anchor, allowing us to define a
desirable (or ideal) disparity profile at every spatial point. 3) By comparing
the desirable and predicted disparity profiles, we can quantify the level of
matching ambiguity between left and right images for confidence measurement.
Extensive experimental results using various stereo-matching networks and
datasets demonstrate that the proposed stereo-confidence method not only shows
competitive performance on its own but also consistent performance improvements
when it is used as an input modality for learning-based stereo-confidence
methods.
Related papers
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching [110.22344879336043]
We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision.
We demonstrate that Stereo Risk enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions.
A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets.
arXiv Detail & Related papers (2024-07-03T14:30:47Z) - Revisiting Domain Generalized Stereo Matching Networks from a Feature
Consistency Perspective [65.37571681370096]
We propose a simple pixel-wise contrastive learning across the viewpoints.
A stereo selective whitening loss is introduced to better preserve the stereo feature consistency across domains.
Our method achieves superior performance over several state-of-the-art networks.
arXiv Detail & Related papers (2022-03-21T11:21:41Z) - Stereo Matching with Cost Volume based Sparse Disparity Propagation [27.74131924190943]
We propose a simple yet novel scheme to improve general stereo matching based on matching cost volume and sparse matching feature points.
Our scheme achieves promising performance comparable to state-of-the-art methods.
arXiv Detail & Related papers (2022-01-28T05:20:41Z) - AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach [50.855679274530615]
We present a novel domain-adaptive approach called AdaStereo to align multi-level representations for deep stereo matching networks.
Our models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo.
Our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
arXiv Detail & Related papers (2021-12-09T15:10:47Z) - On the confidence of stereo matching in a deep-learning era: a
quantitative evaluation [124.09613797008099]
We review more than ten years of developments in the field of confidence estimation for stereo matching.
We study the different behaviors of each measure when applied to a pool of different stereo algorithms and, for the first time in literature, when paired with a state-of-the-art deep stereo network.
arXiv Detail & Related papers (2021-01-02T11:40:17Z) - Stereo Frustums: A Siamese Pipeline for 3D Object Detection [20.443003989363916]
The paper proposes a light-weighted stereo frustums matching module for 3D objection detection.
The proposed framework takes advantage of a high-performance 2D detector and a point cloud segmentation network to regress 3D bounding boxes for autonomous driving vehicles.
arXiv Detail & Related papers (2020-10-27T20:46:17Z) - Self-adapting confidence estimation for stereo [48.56220165347967]
We propose a flexible and lightweight solution enabling self-adapting confidence estimation to the stereo algorithm or network.
Our strategy allows us not only a seamless integration with any stereo system, but also, due to its self-adapting capability, for its out-of-the-box deployment in the field.
arXiv Detail & Related papers (2020-08-14T16:17:28Z) - Learning Stereo Matchability in Disparity Regression Networks [40.08209864470944]
This paper proposes a stereo matching network that considers pixel-wise matchability.
The proposed deep stereo matchability (DSM) framework can improve the matching result or accelerate the computation while still guaranteeing the quality.
arXiv Detail & Related papers (2020-08-11T15:55:49Z) - AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching [50.06646151004375]
A novel domain-adaptive pipeline called AdaStereo aims to align multi-level representations for deep stereo matching networks.
Our AdaStereo models achieve state-of-the-art cross-domain performance on multiple stereo benchmarks, including KITTI, Middlebury, ETH3D, and DrivingStereo.
arXiv Detail & Related papers (2020-04-09T16:15:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.