Related papers: MIDAS: Modeling Ground-Truth Distributions with Da…

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a…

Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities…

End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occur in unseen domains (e.g., when moving from synthetic to…

Motivated by the need to identify erroneous disparity assignments, various approaches for uncertainty and confidence estimation of dense stereo matching have been presented in recent years. As in many other fields, especially deep learning…

Deep learning (DL) methods are widely investigated for stereo image matching tasks due to their reported high accuracies. However, their transferability/generalization capabilities are limited by the instances seen in the training data.…

Existing deep learning based stereo matching methods either focus on achieving optimal performances on the target dataset while with poor generalization for other datasets or focus on handling the cross-domain generalization by suppressing…

Domain generalization aims to learn invariance across multiple training domains, thereby enhancing generalization against out-of-distribution data. While gradient or representation matching algorithms have achieved remarkable success, these…

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…

With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in…

Despite the great success of deep learning in stereo matching, recovering accurate disparity maps is still challenging. Currently, L1 and cross-entropy are the two most widely used losses for stereo network training. Compared with the…

State-of-the-art stereo matching (SM) models trained on synthetic data often fail to generalize to real data domains due to domain differences, such as color, illumination, contrast, and texture. To address this challenge, we leverage data…

Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application. In this paper,…

Although supervised deep stereo matching networks have made impressive achievements, the poor generalization ability caused by the domain gap prevents them from being applied to real-life scenarios. In this paper, we propose to leverage the…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

Nighttime stereo depth estimation is still challenging, as assumptions associated with daytime lighting conditions do not hold any longer. Nighttime is not only about low-light and dense noise, but also about glow/glare, flares, non-uniform…

As overparameterized models become increasingly prevalent, training loss alone offers limited insight into generalization performance. While smoothness has been linked to improved generalization across various settings, directly enforcing…

Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others. Such domain shift issue is usually…

Stereo matching has recently witnessed remarkable progress using Deep Neural Networks (DNNs). But, how robust are they? Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in…

Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary substantially due to environment changes and sensor noises, but…