Speech Enhancement (SE) and Speech Separation (SS) have traditionally been treated as distinct tasks in speech processing. However, real-world audio often involves both background noise and overlapping speakers, motivating the need for a unified solution. While recent approaches have attempted to integrate SE and SS within multi-stage architectures, these approaches typically involve complex, parameter-heavy models and rely on supervised training, limiting scalability and generalization. In this work, we propose UniVoiceLite, a lightweight and unsupervised audiovisual framework that unifies SE and SS within a single model. UniVoiceLite leverages lip motion and facial identity cues to guide speech extraction and employs Wasserstein distance regularization to stabilize the latent space without requiring paired noisy-clean data. Experimental results demonstrate that UniVoiceLite achieves strong performance in both noisy and multi-speaker scenarios, combining efficiency with robust generalization. The source code is available at https://github.com/jisoo-o/UniVoiceLite.

The distribution gap between training data and real-world data often causes significant performance drops in networks trained via naive supervised learning. To address this, domain generalization methods have been developed to gain robust performance in unseen domains. In this paper, we propose a single-domain generalized object detection (S-DGOD) method. Unlike previous works, we utilize both image-level and feature-level augmentations and experimentally demonstrate their synergistic effects. Image-level augmentations expand the source domain, while feature-level augmentations leverage CLIP to incorporate potential domain descriptions. Our method achieves superior performance, with 29.2% mAP on the Cityscapes-C and 37.1% mAP on the Diverse-Weather dataset.

Remote sensing using satellite imagery has been actively researched, inducing various applications of computer vision. In this field, the quality of satellite images is very important in facilitating continuous Earth observation and environmental monitoring. However, even after undergoing various correction processes, satellite images inevitably contain haze and clouds. The presence of these haze and clouds introduces numerous challenges to the acquisition of high-quality satellite images. In this study, we present a novel dehazing method designed to enhance the quality of satellite images named dual frequency pass networks (DFPNs). The proposed method comprises two branches: a transformer branch for capturing low-frequency components and a convolution branch for extracting high-frequency components. Thus, this approach can consider both the global features from the transformer and the local features from the convolution. The experiments demonstrate that the proposed method outperforms other state-of-the-art methods.

In this paper, we propose a novel dehazing method based on self-distillation. In contrast to conventional knowledge distillation approaches that transfer large models (teacher networks) to small models (student networks), we introduce a single knowledge distillation network that transfers network parameters to itself for dehazing. In the early stages, the proposed network transfers scene content (identity) information to the next stage of itself using haze-free data. However, in the later stages, the network transfers haze information to itself using haze data, enabling the accurate dehazing of input images using scene information from the early stages. In a single network, parameters are seamlessly updated from extracting global scene features to dehazing the scene. During the training, forward propagation acts as a teacher network, whereas backward propagation acts as a student network. The experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art dehazing methods.

We present a novel dehazing framework for real-world images that contain both hazy and low-light areas. Dehazing and low-light enhancements are unified by using an illumination map that is estimated using a proposed convolutional neural network. The illumination map is then used as a component for three different tasks: atmospheric light estimation, transmission map estimation, and low-light enhancement, thereby enabling the solving of interrelated low-level vision problems simultaneously. To train the neural network to perform both dehazing and low-light enhancement, we synthesize hazy and low-light images from normal images. Experimental results demonstrate that the proposed method quantitatively and qualitatively outperforms state-of-the-art algorithms in real-world image dehazing.

We propose a highly generative dehazing method based on pixel-wise Wasserstein autoencoders. In contrast to existing dehazing methods based on generative adversarial networks, our method can produce a variety of dehazed images with different styles. It significantly improves the dehazing accuracy via pixel-wise matching from hazy to dehazed images through 2-dimensional latent tensors of the Wasserstein autoencoder. In addition, we present an advanced feature fusion technique to deliver rich information to the latent space. For style transfer, we introduce a mapping function that transforms existing latent spaces to new ones. Thus, our method can produce highly generative haze-free images with various tones, illuminations, and moods, which induces several interesting applications, including low-light enhancement, daytime dehazing, nighttime dehazing, and underwater image enhancement. Experimental results demonstrate that our method quantitatively outperforms existing state-of-the-art methods for synthetic and real-world datasets, and simultaneously generates highly generative haze-free images, which are qualitatively diverse.

We propose a low-light enhancement method using an advanced generative adversarial network (GAN) and a task-driven training set. Unlike traditional training sets that only synthesize global illumination, we apply local illumination to make the training images. Furthermore, we enhance traditional GANs with spectral normalization and advanced loss functions, making training stable and leading to accurate results. Experimental results show that our method outperforms state-of-the art methods qualitatively and quantitatively and alleviates saturation problems in bright areas, which typically occur after traditional low-light enhancements.

Here, the authors propose a novel tracking algorithm that can automatically modify the initial configuration of a target to improve the tracking accuracy in subsequent frames. To achieve this goal, the authors’ method analyses the likelihood landscape (LL) for the image patch described by the initial configuration. A good configuration has a unimodal distribution with a steep shape in the LL. Using the LL analysis, the authors’ method improves the initial configuration, resulting in more accurate tracking results. The authors improve the conventional LL analysis based on two ideas. First, the authors’ method analyses the LL in the RGB space rather than the grey space. Second, the method introduces an additional criterion for a good configuration: a high likelihood value at the mode. The authors further enhance their method through post‐processing of the visual tracking results at each frame, where the estimated bounding boxes are modified by the LL analysis. The experimental results demonstrate that the authors’ advanced LL analysis helps improve the tracking accuracy of several baseline trackers on a visual tracking benchmark data set. In addition, the authors’ simple post‐processing technique significantly enhances the visual tracking performance in terms of precision and success rate.

We present a novel deep learning-based dehazing method using adaptive patch splits. Our method applies quad-tree decomposition to an input image, yielding multiple patches with adaptive sizes. Then, each patch is fed into a Convolutional Neural Network (CNN) and classified into a single transmission value, in which a transmission map comprises transmission values from all patches. Homogeneous regions in the image are typically decomposed into large patches. Thus the method can save computational cost. Non-homogeneous regions are divided into small patches, which helps preserve local details in a transmission map. To train CNN, we synthesize numerous hazy images from haze-free images. Experimental results demonstrate our method surpasses state- of-the-art deep learning based algorithms quantitatively and qualitatively.