English
Related papers

Related papers: Improving Feature Stability during Upsampling -- S…

200 papers

Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Long Peng , Anran Wu , Wenbo Li , Peizhe Xia , Xueyuan Dai , Xinjie Zhang , Xin Di , Haoze Sun , Renjing Pei , Yang Wang , Yang Cao , Zheng-Jun Zha

Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Chen Wei , Lingxi Xie , Xutong Ren , Yingda Xia , Chi Su , Jiaying Liu , Qi Tian , Alan L. Yuille

We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…

Machine Learning · Computer Science 2021-04-07 Boyuan Chen , Yu Li , Sunand Raghupathi , Hod Lipson

Artifact detectors have been shown to enhance the performance of image-generative models by serving as reward models during fine-tuning. These detectors enable the generative model to improve overall output fidelity and aesthetics. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Dennis Menn , Feng Liang , Diana Marculescu

The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Lu Xiao , Jiale Zhang , Yang Liu , Taicheng Huang , Xin Tian

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Computer Vision and Pattern Recognition · Computer Science 2019-09-23 Nikita Dvornik , Julien Mairal , Cordelia Schmid

This paper proposes a method for unsupervised anomalous sound detection (UASD) and captioning the reason for detection. While there is a method that captions the difference between given normal and anomalous sound pairs, it is assumed to be…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-30 Ryoya Ogura , Tomoya Nishida , Yohei Kawaguchi

As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Yuanhao Zhai , Tianyu Luan , David Doermann , Junsong Yuan

Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Evangelos Ntavelis , Mohamad Shahbazi , Iason Kastanis , Radu Timofte , Martin Danelljan , Luc Van Gool

Image compression with upsampling encodes information to succeedingly increase image resolution, for example by encoding differences in FUIF and JPEG XL. It is useful for progressive decoding, also often can improve compression ratio - both…

Image and Video Processing · Electrical Eng. & Systems 2020-07-14 Jarek Duda

Spatial sampling is traditionally studied in a static setting where static sensors scattered around space take measurements of the spatial field at their locations. In this paper we study the emerging paradigm of sampling and reconstructing…

Multimedia · Computer Science 2015-06-12 Jayakrishnan Unnikrishnan , Martin Vetterli

Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts…

Computer Vision and Pattern Recognition · Computer Science 2016-08-22 Aaron van den Oord , Nal Kalchbrenner , Koray Kavukcuoglu

Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time. This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Jianfeng Wang , Daniela Massiceti , Xiaolin Hu , Vladimir Pavlovic , Thomas Lukasiewicz

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…

Computer Vision and Pattern Recognition · Computer Science 2021-03-10 Giancarlo Di Biase , Hermann Blum , Roland Siegwart , Cesar Cadena

To increase the flexibility and scalability of deep neural networks for image reconstruction, a framework is proposed based on bandpass filtering. For many applications, sensing measurements are performed indirectly. For example, in…

Computer Vision and Pattern Recognition · Computer Science 2018-11-27 Joseph Y. Cheng , Feiyu Chen , Marcus T. Alley , John M. Pauly , Shreyas S. Vasanawala

Purpose: Compressed sensing MRI (CS-MRI) from single and parallel coils is one of the powerful ways to reduce the scan time of MR imaging with performance guarantee. However, the computational costs are usually expensive. This paper aims to…

Computer Vision and Pattern Recognition · Computer Science 2017-03-06 Dongwook Lee , Jaejun Yoo , Jong Chul Ye

Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Lingzhi Zhang , Zhengjie Xu , Connelly Barnes , Yuqian Zhou , Qing Liu , He Zhang , Sohrab Amirghodsi , Zhe Lin , Eli Shechtman , Jianbo Shi

Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Niccolò Biondi , Federico Pernici , Simone Ricci , Alberto Del Bimbo

Though semantic segmentation has been heavily explored in vision literature, unique challenges remain in the remote sensing domain. One such challenge is how to handle resolution mismatch between overhead imagery and ground-truth label…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Scott Workman , Armin Hadzic , M. Usman Rafique

Stochastic sampling techniques are ubiquitous in real-time rendering, where performance constraints force the use of low sample counts, leading to noisy intermediate results. To remove this noise, the post-processing step of temporal and…

Graphics · Computer Science 2023-10-25 William Donnelly , Alan Wolfe , Judith Bütepage , Jon Valdés