English
Related papers

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

200 papers

In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Cheng Zhang , Shaolin Su , Yu Zhu , Qingsen Yan , Jinqiu Sun , Yanning Zhang

Recent advancements in sRGB-to-RAW de-rendering have increasingly emphasized metadata-driven approaches to reconstruct RAW data from sRGB images, supplemented by partial RAW information. In image-based de-rendering, metadata is commonly…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Hongjun Chen , Wencheng Han , Huan Zheng , Jianbing Shen

Remote sensing change detection, identifying changes between scenes of the same location, is an active area of research with a broad range of applications. Recent advances in multimodal self-supervised pretraining have resulted in…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Isaac Corley , Peyman Najafirad

The entire Image Signal Processor (ISP) of a camera relies on several processes to transform the data from the Color Filter Array (CFA) sensor, such as demosaicing, denoising, and enhancement. These processes can be executed either by some…

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Gabriela Csurka

Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Alaaeldin El-Nouby , Natalia Neverova , Ivan Laptev , Hervé Jégou

Existing multi-view image generation methods often make invasive modifications to pre-trained text-to-image (T2I) models and require full fine-tuning, leading to (1) high computational costs, especially with large base models and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Zehuan Huang , Yuan-Chen Guo , Haoran Wang , Ran Yi , Lizhuang Ma , Yan-Pei Cao , Lu Sheng

Image retouching has received significant attention due to its ability to achieve high-quality visual content. Existing approaches mainly rely on uniform pixel-wise color mapping across entire images, neglecting the inherent color…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Hancheng Zhu , Xinyu Liu , Rui Yao , Kunyang Sun , Leida Li , Abdulmotaleb El Saddik

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data) or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Mahmoud Afifi , Abdelrahman Abdelhamed , Abdullah Abuolaim , Abhijith Punnappurath , Michael S. Brown

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…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Wenzheng Song , Masanori Suganuma , Xing Liu , Noriyuki Shimobayashi , Daisuke Maruta , Takayuki Okatani

Supervised learning with a convolutional neural network is recognized as a powerful means of image restoration. However, most such methods have been designed for application to grayscale and/or color images; therefore, they have limited…

Image and Video Processing · Electrical Eng. & Systems 2019-07-02 Ryuji Imamura , Tatsuki Itasaka , Masahiro Okuda

We present a general learning-based solution for restoring images suffering from spatially-varying degradations. Prior approaches are typically degradation-specific and employ the same processing across different images and different pixels…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Kuldeep Purohit , Maitreya Suin , A. N. Rajagopalan , Vishnu Naresh Boddeti

High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing…

Image and Video Processing · Electrical Eng. & Systems 2023-09-06 Yunhao Zou , Chenggang Yan , Ying Fu

Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many…

Image and Video Processing · Electrical Eng. & Systems 2020-02-17 Amey Chaware , Colin L. Cooke , Kanghyun Kim , Roarke Horstmeyer

Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer…

Image and Video Processing · Electrical Eng. & Systems 2019-11-15 Chyuan-Tyng Wu , Leo F. Isikdogan , Sushma Rao , Bhavin Nayak , Timo Gerasimow , Aleksandar Sutic , Liron Ain-kedem , Gilad Michael

Pansharpening is a challenging image fusion task that involves restoring images using two different modalities: low-resolution multispectral images (LRMS) and high-resolution panchromatic (PAN). Many end-to-end specialized models based on…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 RuoCheng Wu , ZiEn Zhang , ShangQi Deng , YuLe Duan , LiangJian Deng

What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image…

Low light conditions not only degrade human visual experience, but also reduce the performance of downstream machine analytics. Although many works have been designed for low-light enhancement or domain adaptive machine analytics, the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Wenjing Wang , Zhengbo Xu , Haofeng Huang , Jiaying Liu

The emergence of large models, also known as foundation models, has brought significant advancements to AI research. One such model is Segment Anything (SAM), which is designed for image segmentation tasks. However, as with other foundation…

Computer Vision and Pattern Recognition · Computer Science 2023-05-03 Tianrun Chen , Lanyun Zhu , Chaotao Ding , Runlong Cao , Yan Wang , Zejian Li , Lingyun Sun , Papa Mao , Ying Zang

Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability…

Computer Vision and Pattern Recognition · Computer Science 2023-01-23 Fang Peng , Xiaoshan Yang , Linhui Xiao , Yaowei Wang , Changsheng Xu