Related papers: Transformer based Pluralistic Image Completion wit…

Due to the lack of a definitive ground truth for the image fusion problem, the loss functions are structured based on evaluation metrics, such as the structural similarity index measure (SSIM). However, in doing so, a bias is introduced…

Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most of the recent…

Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and scalability. Recent attempts to leverage pretrained visual…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predominantly attempts to address this in a dual encoder paradigm,…

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…

In this paper, we present a novel image inpainting technique using frequency domain information. Prior works on image inpainting predict the missing pixels by training neural networks using only the spatial domain information. However,…

We study the problem of multimodal fusion in this paper. Recent exchanging-based methods have been proposed for vision-vision fusion, which aim to exchange embeddings learned from one modality to the other. However, most of them project…

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Image enhancement is a technique that frequently utilized in digital image processing. In recent years, the popularity of learning-based techniques for enhancing the aesthetic performance of photographs has increased. However, the majority…

The aim of multispectral image fusion is to combine object or scene features of images with different spectral characteristics to increase the perceptual quality. In this paper, we present a novel learning-based solution to image fusion…

Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…

Modern smartphone camera quality heavily relies on the image signal processor (ISP) to enhance captured raw images, utilizing carefully designed modules to produce final output images encoded in a standard color space (e.g., sRGB).…

Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

Autoregressive transformers have revolutionized high-fidelity image generation. One crucial ingredient lies in the tokenizer, which compresses high-resolution image patches into manageable discrete tokens with a scanning or hierarchical…

Image deblurring continues to achieve impressive performance with the development of generative models. Nonetheless, there still remains a displeasing problem if one wants to improve perceptual quality and quantitative scores of recovered…

In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the unsupervised image-to-image…

Video inpainting tasks have seen significant improvements in recent years with the rise of deep neural networks and, in particular, vision transformers. Although these models show promising reconstruction quality and temporal consistency,…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…