Related papers: Continual Test-Time Adaptation for Single Image De…

Scene text image super-resolution aims to increase the resolution and readability of the text in low-resolution images. Though significant improvement has been achieved by deep convolutional neural networks (CNNs), it remains difficult to…

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce…

Recent years have witnessed the remarkable performance of diffusion models in various vision tasks. However, for image restoration that aims to recover clear images with sharper details from given degraded observations, diffusion-based…

State-of-the-art person re-identification systems that employ a triplet based deep network suffer from a poor generalization capability. In this paper, we propose a four stream Siamese deep convolutional neural network for person…

Recent advances in model pre-training give rise to task adaptation-based few-shot learning (FSL), where the goal is to adapt a pre-trained task-agnostic model for capturing task-specific knowledge with a few-labeled support samples of the…

In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction…

Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory…

Image demosaicing is an important step in the image processing pipeline for digital cameras. In data centric approaches, such as deep learning, the distribution of the dataset used for training can impose a bias on the networks' outcome.…

Recent self-supervised methods are mainly designed for representation learning with the base model, e.g., ResNets or ViTs. They cannot be easily transferred to DETR, with task-specific Transformer modules. In this work, we present Siamese…

Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…

Traditional reconstruction-based methods have struggled to achieve competitive performance in anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD), a novel denoising process for image reconstruction…

Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model…

Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…

Moire artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera. Existing deep learning-based demoireing methods trained on large scale…

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for…

Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…

Semantic Change Detection (SCD) in remote sensing imagery requires accurately identifying land-cover changes across multi-temporal image pairs. Despite substantial advancements, including the introduction of transformer-based architectures,…

Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich representations of large pretrained models with minimal…

Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local corruption patterns without test-time degradation labels.…

Autonomous driving has attracted much attention over the years but turns out to be harder than expected, probably due to the difficulty of labeled data collection for model training. Self-supervised learning (SSL), which leverages unlabeled…