Related papers: TRIP: Refining Image-to-Image Translation via Riva…

The rise of personalized generative models raises a central question: how should we evaluate identity preservation? Given a reference image (e.g., one's pet), we expect the generated image to retain precise details attached to the subject's…

Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities. However, GANs are notoriously difficult to train: Mode collapse and other instabilities in the…

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where…

Text-to-Image translation has been an active area of research in the recent past. The ability for a network to learn the meaning of a sentence and generate an accurate image that depicts the sentence shows ability of the model to think more…

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for this task: 1) lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we…

Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…

The goal of attribute manipulation is to control specified attribute(s) in given images. Prior work approaches this problem by learning disentangled representations for each attribute that enables it to manipulate the encoded source…

Content creation and image editing can benefit from flexible user controls. A common intermediate representation for conditional image generation is a semantic map, that has information of objects present in the image. When compared to raw…

In this paper, we propose a multi-stage and high-resolution model for image synthesis that uses fine-grained attributes and masks as input. With a fine-grained attribute, the proposed model can detailedly constrain the features of the…

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.…

For semantic-guided cross-view image translation, it is crucial to learn where to sample pixels from the source view image and where to reallocate them guided by the target view semantic map, especially when there is little overlap or…

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two…

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich…

Reasoning-based image quality assessment (IQA) models trained through reinforcement learning (RL) exhibit exceptional generalization, yet the underlying mechanisms and critical factors driving this capability remain underexplored in current…

Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected…

Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing frameworks operate in a training-free manner. They rely on heuristic task scheduling and exhaustive…

Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years. The success of translation mainly relies on the network architecture to…

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods…