Related papers: RAW-Adapter: Adapting Pre-trained Visual Model to …

In this paper, we propose a principled Perceptual Adversarial Networks (PAN) for image-to-image transformation tasks. Unlike existing application-specific algorithms, PAN provides a generic framework of learning mapping relationship between…

With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs has become increasingly important. Existing VLMs predominantly digest and understand…

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which…

Deep learning-based blind image deblurring plays an essential role in solving image blur since all existing kernels are limited in modeling the real world blur. Thus far, researchers focus on powerful models to handle the deblurring problem…

Enhancing RAW images captured under low light conditions is a challenging task. Recent deep learning based RAW enhancement methods have shifted from using real paired data to relying on synthetic datasets. These synthetic datasets are…

Background: Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water. In addition, the degree of attenuation varies with the…

Imitation Learning can train robots to perform complex and diverse manipulation tasks, but learned policies are brittle with observations outside of the training distribution. 3D scene representations that incorporate observations from…

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V)…

Recently, multiple synthetic and real-world datasets have been built to facilitate the training of deep single image reflection removal (SIRR) models. Meanwhile, diverse testing sets are also provided with different types of reflection and…

Recent advances in video captioning are driven by large-scale pretrained models, which follow the standard "pre-training followed by fine-tuning" paradigm, where the full model is fine-tuned for downstream tasks. Although effective, this…

Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…

The deep learning (DL)-based methods of low-level tasks have many advantages over the traditional camera in terms of hardware prospects, error accumulation and imaging effects. Recently, the application of deep learning to replace the image…

Deep image compression performs better than conventional codecs, such as JPEG, on natural images. However, deep image compression is learning-based and encounters a problem: the compression performance deteriorates significantly for…

Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB…

Visual prompting (VP) has emerged as a popular method to repurpose pretrained vision models for adaptation to downstream tasks. Unlike conventional model fine-tuning techniques, VP introduces a universal perturbation directly into the input…

RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their direct use in downstream computer vision tasks. Prior methods…

Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…

This paper considers matching images of low-light scenes, aiming to widen the frontier of SfM and visual SLAM applications. Recent image sensors can record the brightness of scenes with more than eight-bit precision, available in their…

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-then-finetune"…

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…