paper-with-me

홈 › Papers

A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models

2024-03-15 · Xijun Wang, Santiago López-Tapia, Alice Lucas, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos

Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.

📄 PDF Abstract BibTeX arXiv:2403.10589

Code (0)

등록된 구현이 없습니다.

Tasks

Super-Resolution

Similar Papers 제목 키워드 기반

Learning Content-Weighted Deep Image Compression

2019-04-01 · Mu Li, WangMeng Zuo, Shuhang Gu, Jane You 외

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approx…

DecoderImage Compression

LG-Hand: Advancing 3D Hand Pose Estimation with Locally and Globally Kinematic Knowledge

2022-11-06 · Tu Le-Xuan, Trung Tran-Quang, Thi Ngoc Hien Doan, Thanh-Hai Tran

3D hand pose estimation from RGB images suffers from the difficulty of obtaining the depth information. Therefore, a great deal of attention has been spent on estimating 3D hand pose from 2D hand joints. In this paper, w…

3D Hand Pose EstimationHand Pose EstimationPose Estimation

Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction

2023-06-28 · Aoqi Guo, Junnan Wu, Peng Gao, Wenbo Zhu 외

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target …

Dimensionality ReductionSpeech ExtractionSpeech Separation

Loss functions incorporating auditory spatial perception in deep learning -- a review

2025-06-24 · Boaz Rafaely, Stefan Weinzierl, Or Berebi, Fabian Brinkmann

Binaural reproduction aims to deliver immersive spatial audio with high perceptual realism over headphones. Loss functions play a central role in optimizing and evaluating algorithms that generate binaural signals. Howev…

Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation

2023-10-02 · Xiaohang Xu, Toyotaro Suzumura, Jiawei Yong, Masatoshi Hanai 외

Next Point-of-Interest (POI) recommendation plays a crucial role in urban mobility applications. Recently, POI recommendation models based on Graph Neural Networks (GNN) have been extensively studied and achieved, howeve…