paper-with-me

Papers

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

2020-09-30 · Sijin Kim, Namhyuk Ahn, Kyung-Ah Sohn

In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may not be suitable for many real-world applications. To deal with such cases, some studies have proposed sequentially combined distortions datasets. Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image. In addition, we also propose a mixture of experts network to effectively restore a multi-distortion image. Motivated by the multi-task learning, we design our network to have multiple paths that learn both common and distortion-specific representations. Our model is effective for restoring real-world distortions and we experimentally verify that our method outperforms other models designed to manage both single distortion and multiple distortions.

📄 PDF Abstract BibTeX arXiv:2009.14563

Code (1)

SijinKim/mepsnet 공식 구현 pytorch

Tasks

Mixture-of-ExpertsMulti-Task Learning

Similar Papers 제목 키워드 기반

Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment

2025-01-01 · CVPR 2025 1 · Xudong Li, Wenjie Nie, Yan Zhang, Runze Hu 외

In the Blind Image Quality Assessment (BIQA) field, accurately assessing the quality of authentically distorted images presents a substantial challenge due to the diverse distortion types in natural settings. Existin…

Blind Image Quality AssessmentImage Quality AssessmentKnowledge DistillationLocal Distortion

Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions

2018-12-03 · CVPR 2019 6 · Masanori Suganuma, Xing Liu, Takayuki Okatani

Many studies have been conducted so far on image restoration, the problem of restoring a clean image from its distorted version. There are many different types of distortion which affect image quality. Previous studies h…

Image Restoration

Quality Resilient Deep Neural Networks

2017-03-23 · Samuel Dodge, Lina Karam

We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. Howeve…

Mixture-of-Experts

On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting

2026-07-09 · In-Hwan Jin, Hyeongju Mun, Joonsoo Kim, Kugjin Yun 외 arxiv

Dynamic scene reconstruction remains challenging due to the heterogeneous and spatially varying nature of real-world motion. Although recent 3D Gaussian Splatting methods have introduced diverse deformation formulations …

Novel View Synthesis

TrajMoE: Spatially-Aware Mixture of Experts for Unified Human Mobility Modeling

2025-05-24 · Chonghua Han, Yuan Yuan, Kaiyan Chen, Jingtao Ding 외

Modeling human mobility across diverse cities is essential for applications such as urban planning, transportation optimization, and personalized services. However, generalization remains challenging due to heterogeneous…

Mixture-of-Experts