Papers with Code 아카이브
Image Super-Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 69
- 보존된 평가 기록
- 748
Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network
Effect of Super Resolution on High Dimensional Features for Unsupervised Face Recognition in the Wild
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image
Single image super-resolution using self-optimizing mask via fractional-order gradient interpolation and reconstruction
Understanding Traffic Density from Large-Scale Web Camera Data
Convolutional Low-Resolution Fine-Grained Classification
GUN: Gradual Upsampling Network for Single Image Super-Resolution
Local Patch Encoding-Based Method for Single Image Super-Resolution
DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
Manifold Based Low-rank Regularization for Image Restoration and Semi-supervised Learning
Evolving Boxes for Fast Vehicle Detection
Language Independent Single Document Image Super-Resolution using CNN for improved recognition
Super-resolution Using Constrained Deep Texture Synthesis
Dual Recovery Network with Online Compensation for Image Super-Resolution
Joint Dictionary Learning for Example-based Image Super-resolution
Light Field Super-Resolution Via Graph-Based Regularization
Learning a Mixture of Deep Networks for Single Image Super-Resolution
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Learning a No-Reference Quality Metric for Single-Image Super-Resolution
Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution
A Large-scale Distributed Video Parsing and Evaluation Platform
3D Fully Convolutional Network for Vehicle Detection in Point Cloud
Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
Amortised MAP Inference for Image Super-resolution
Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?
Sparsity-based Color Image Super Resolution via Exploiting Cross Channel Constraints
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
Transport-based analysis, modeling, and learning from signal and data distributions
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
A Boosting Method to Face Image Super-resolution
Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution
Vehicle Detection from 3D Lidar Using Fully Convolutional Network
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Accelerating the Super-Resolution Convolutional Neural Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.