Related papers: AdaStereo: An Efficient Domain-Adaptive Stereo Mat…

We introduce a novel approach for adapting deep stereo networks in a collaborative manner. By building over principles of federated learning, we develop a distributed framework allowing for demanding the optimization process to a number of…

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First,…

We present an improved three-step pipeline for the stereo matching problem and introduce multiple novelties at each stage. We propose a new highway network architecture for computing the matching cost at each possible disparity, based on…

We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding…

Recently, end-to-end deep networks based stereo matching methods, mainly because of their performance, have gained popularity. However, this improvement in performance comes at the cost of increased computational and memory bandwidth…

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and…

This paper proposes a new framework for depth completion robust against domain-shifting issues. It exploits the generalization capability of modern stereo networks to face depth completion, by processing fictitious stereo pairs obtained…

We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt…

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it…

While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…

We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that…

In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but…

Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue. Although self-supervised learning has recently spread…

It is well known that we need to choose the hyper-parameters in Momentum, AdaGrad, AdaDelta, and other alternative stochastic optimizers. While in many cases, the hyper-parameters are tuned tediously based on experience becoming more of an…

This paper presents a novel general-purpose guided stereo paradigm that mimics the active stereo principle by replacing the unreliable physical pattern projector with a depth sensor. It works by projecting virtual patterns consistent with…

Domain adaptation for semantic segmentation enables to alleviate the need for large-scale pixel-wise annotations. Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in…

In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…

Recent stereo matching networks achieves dramatic performance by introducing epipolar line constraint to limit the matching range of dual-view. However, in complicated real-world scenarios, the feature information based on intra-epipolar…