- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Recurrent conditional generative adversarial network for image deblurring
摘要： Nowadays, there is an increasing demand for images with high definition and fine textures, but images captured in natural scenes usually suffer from complicated blurry artifacts, caused mostly by object motion or camera shaking. Since these annoying artifacts greatly decrease image visual quality, deblurring algorithms have been proposed from various aspects. However, most energy-optimization-based algorithms rely heavily on blur kernel priors, and some learning-based methods either adopt pixel-wise loss function or ignore global structural information. Therefore, we propose an image deblurring algorithm based on recurrent conditional generative adversarial network (RCGAN), in which the scale-recurrent generator extracts sequence spatio-temporal features and reconstructs sharp images in a coarse-to-fine scheme. To thoroughly evaluate the global and local generator performance, we further propose a receptive field recurrent discriminator. Besides, the discriminator takes blurry images as conditions, which help to differentiate reconstructed images from real sharp ones. Last but not least, since the gradients are vanishing when training generator with the output of discriminator, a progressive loss function is proposed to enhance the gradients in back-propagation and to take full advantages of discriminative features. Extensive experiments prove the superiority of RCGAN over state-of-the-art algorithms both qualitatively and quantitatively.
关键词： coarse-to-fine,Image deblurring,receptive field recurrent,conditional generative adversarial network
更新于2025-09-23 15:23:52
-
Large scale image retrieval with DCNN and local geometrical constraint model
摘要： Image retrieval, which refers to browse, search and retrieve the images of the same scene or object from a large database of digital images, has attracted increasing interests in recent years. This paper proposes a coarse-to-fine method for fast indexing with Deep Convolutional Neural Network(DCNN) and Local Geometrical Constraint Model. We first use a vector quantized DCNN feature descriptors and exploit enhanced Locality-sensitive hashing(LSH) techniques for fast coarse-grained retrieval. Then, we focus on obtaining high-precision preserved matches for fine-grained retrieval. This is formulated as a maximum likelihood estimation of a Bayesian model with latent variables indicating whether matches in the putative set are inliers or outliers. We impose the non-parametric global geometrical constraints on the correspondence using Tikhonov regularizers in a reproducing kernel Hilbert space. To ensure the well-posedness of the problem, we develop a local geometrical constraint that can preserve local structures among neighboring feature points, and it is also robust to a large number of outliers. The problem is solved by using the Expectation Maximization algorithm. Extensive experiments on real near-duplicate images for both feature matching and image retrieval demonstrate that the results of the proposed method outperform current state-of-the-art methods.
关键词： Image retrieval,Coarse-to-fine,Local geometrical constraint model,DCNN
更新于2025-09-23 15:23:52
-
A Coarse-to-Fine Method for Infrared Small Target Detection
摘要： Infrared small target detection in a complex background is a challenging problem. A complex background generally contains structured edges, unstructured clutter, and noise, which completely have different properties. It is very difficult to separate small target from these interferences by exploiting one property. To solve this problem, we propose a coarse-to-fine method to gradually detect small target. In the coarse phase, nonlocal self-similarity property of the structured edges is exploited so as to separate the structured edges from the other components, such as the random noise, the unstructured clutter, and also the small target. In the fine phase, we utilize the local contrast prior of the small target in a local region so as to distinguish the small target from the unstructured clutter and noise. Multiscale information is further introduced to accommodate the changing size of the small target. This progressive detection pipeline utilizes the nonlocal, local, and multiscale information in a single image, which facilitates gradually differentiating the small target from the structured edges, unstructured clutter, and noise. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods.
关键词： nonlocal self-similarity,infrared small target detection,Coarse to fine (CF),multiscale,local contrast
更新于2025-09-10 09:29:36
-
Dim and small infrared target fast detection guided by visual saliency
摘要： In order to detect dim and small infrared targets from a mass of high-resolution images of omni-directional Infrared Search and Track (IRST) systems rapidly and accurately, a fast target detection method guided by visual saliency (TDGS) is proposed. In this method, a coarse-to-fine detection strategy is used. First, in the stage of coarse-detection, according to the differences of global features between targets and backgrounds, a global saliency model based on fast spectral scale space (FSSS) is constructed to suppress complex background regions rapidly. And visual salient regions which contain dim and small targets are extracted from the original image. Then, in the stage of fine-detection, according to differences of local contrast between targets and background, an adaptive local contrast method (ALCM) is applied to finely improve contrast of targets in visual salient regions. Candidate targets can be further extracted through the adaptive threshold segmentation. Finally, dim and small targets are detected by their temporal relativity in multi-frames. Experimental results on four typical image sequences have indicated that the proposed method can not only detect dim and small infrared targets with small amount of computation, high detection probability, and low false alarm rate, but also adapt to various complex backgrounds. It is suitable for dim and small targets detection in omni-directional IRST systems and other practical applications.
关键词： Visual saliency,Coarse-to-fine detection strategy,Dim and small infrared target,Fast detection,Complex backgrounds
更新于2025-09-09 09:28:46