Related papers: InstaFormer: Instance-Aware Image-to-Image Transla…
We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoencoder architecture with fixed weights. For each task we…
Cross-domain image-to-image translation should satisfy two requirements: (1) preserve the information that is common to both domains, and (2) generate convincing images covering variations that appear in the target domain. This is…
State-of-the-art image-to-image translation methods tend to struggle in an imbalanced domain setting, where one image domain lacks richness and diversity. We introduce a new unsupervised translation network, BalaGAN, specifically designed…
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural…
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired…
Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…
Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based…
This paper proposes the first pure Transformer structure inversion network called SwinStyleformer, which can compensate for the shortcomings of the CNNs inversion framework by handling long-range dependencies and learning the global…
While Text-to-Image (T2I) diffusion models excel at generating visually appealing images of individual instances, they struggle to accurately position and control the features generation of multiple instances. The Layout-to-Image (L2I) task…
Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the…
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).…
We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works…
Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because…
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables…
We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training,…
Automatic transcription of scene understanding in images and videos is a step towards artificial general intelligence. Image captioning is a nomenclature for describing meaningful information in an image using computer vision techniques.…
Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…
Conversion of one font to another font is very useful in real life applications. In this paper, we propose a Convolutional Recurrent Generative model to solve the word level font transfer problem. Our network is able to convert the font…
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…