Showing papers on "Real image published in 2022"
TL;DR: A novel domain-invariant Suction Quality Neural Network (diSQNN) is proposed to fuse realistic color feature and adversarial depth feature with a domain discriminator on depth extractor to reduce simulation-to-reality gap from synthetic images to low-quality RGB-D camera.
6 citations
TL;DR: HSGAN as mentioned in this paper alleviates the mode collapse problem by maintaining a certain distance between the latent code of the generated data and the real data, where the objective function is designed to minimize the f-divergence between the distributions of generated and real data.
5 citations
TL;DR: Zhang et al. as discussed by the authors proposed a cooperative game framework for joint image restoration and edge detection, which consists of two objective functions, one aims to detect edges from the unknown real image, the other aims to restore the unseen real image with supervision of the detected edges.
5 citations
TL;DR: In this article, a filtering algorithm called PerSplat based on topological persistence (a technique used in topological data analysis) was developed to improve segmentation quality, where the ground truth values for the microstructure characteristics are known.
4 citations
01 Jan 2022
1 citations
DOI•
01 Jan 2022TL;DR: In this article, an image repair model based on deep residual network is proposed, which is divided into repair module and mitigation module, and the two modules coordinate with each other to make the image repair effect closer to the real image.
Abstract: In recent years, deep learning has shown significant advantages in image restoration. Compared with the traditional repair method, the image repair method based on deep learning can better solve the problem of image missing blur, but it will also cause the problem of local color difference of the repair image. In this paper, an image repair model based on deep residual network is proposed, which is divided into repair module and mitigation module. The repair module uses part of the convolution network to repair the missing area of image blur, the mitigation module uses the deep residual network to adjust the color difference of the repaired image, and the two modules coordinate with each other to make the image repair effect closer to the real image. The experimental results show that the method proposed in this paper has better effect on image repair.
TL;DR: Li et al. as discussed by the authors proposed a domain adaptation-based approach for indoor image localization, which consists of a multi-level constrained pose regression network and a feature-level discriminator network.
Abstract: Although the deep learning-based indoor image localization has made significant improvement in terms of accuracy, efficiency, and storage requirement of large indoor scenes, the need for collecting huge labeled training data severely limits its practical application. Recently, the synthetic images rendered from widely available 3D models have shown promising potential to relieve the data collection problem. However, due to the dramatic differences between the synthetic and real images, the localization accuracy of approaches trained on synthetic images is not comparable to the methods trained on real images. In this paper, we propose a domain adaptation-based approach to address this issue. Specifically, the proposed approach mainly contains a model consisting of a multi-level constrained pose regression network and a feature-level discriminator network. The discriminator network forces the pose regression network to generate domain-invariant features from real and synthetic images by adversarial learning and thus reduces the performance gaps. In addition, the multi-level constraints further enhance the localization accuracy of pose regression. We perform extensive experiments on open-source rendering images in different settings. The results show that the proposed method significantly improves the performance. The code for the proposed work is available at https://github.com/lqing900205/BIM_domainadaptation.