Related papers: UHD Image Dehazing via anDehazeFormer with Atmosph…
Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather…
Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning,…
The rapid advancement of generative models has led to a growing prevalence of highly realistic AI-generated images, posing significant challenges for digital forensics and content authentication. Conventional detection methods mainly rely…
Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…
A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…
Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing…
Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Convolutional neural networks have achieved excellent results in compressed video quality enhancement task in recent years. State-of-the-art methods explore the spatiotemporal information of adjacent frames mainly by deformable convolution.…
Image dehazing has drawn a significant attention in recent years. Learning-based methods usually require paired hazy and corresponding ground truth (haze-free) images for training. However, it is difficult to collect real-world image pairs,…
The large language model and high-level vision model have achieved impressive performance improvements with large datasets and model sizes. However, low-level computer vision tasks, such as image dehaze and blur removal, still rely on a…
Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve efficiency via latent-space processing, their Gaussian…
Image restoration under hazy weather condition, which is called single image dehazing, has been of significant interest for various computer vision applications. In recent years, deep learning-based methods have achieved success. However,…
Deep learning based methods have achieved significant success in the task of single image reflection removal (SIRR). However, the majority of these methods are focused on High-Definition/Standard-Definition (HD/SD) images, while ignoring…
Hazy images reduce the visibility of the image content, and haze will lead to failure in handling subsequent computer vision tasks. In this paper, we address the problem of image dehazing by proposing a dehazing network named T-Net, which…
Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing…
Recently, there has been rapid and significant progress on image dehazing. Many deep learning based methods have shown their superb performance in handling homogeneous dehazing problems. However, we observe that even if a carefully designed…
Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine…
On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, memory, and latency…
Ultra-high-definition (UHD) image restoration aims to specifically solve the problem of quality degradation in ultra-high-resolution images. Recent advancements in this field are predominantly driven by deep learning-based innovations,…