Papers with Code 아카이브
Super-Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 1
- 보존된 평가 기록
- 1
Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.
<span style="color:grey; opacity: 0.6">( Credit: MemNet )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution
Rethinking Image Evaluation in Super-Resolution
A super-resolution reconstruction method for lightweight building images based on an expanding feature modulation network
RainScaleGAN: a Conditional Generative Adversarial Network for Rainfall Downscaling
C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution
TriLiteNet: Lightweight Model for Multi-Task Visual Perception
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution
Fourier Neural Operator based surrogates for $CO_2$ storage in realistic geologies
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement
FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution
Dual-domain Modulation Network for Lightweight Image Super-Resolution
Automatic quality control in multi-centric fetal brain MRI super-resolution reconstruction
RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification
SASNet: Spatially-Adaptive Sinusoidal Neural Networks
Resolution Invariant Autoencoder
MegaSR: Mining Customized Semantics and Expressive Guidance for Image Super-Resolution
Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution
QUIET-SR: Quantum Image Enhancement Transformer for Single Image Super-Resolution
Reconstruct Anything Model: a lightweight foundation model for computational imaging
Over-the-Air Time-Frequency Synchronization in Distributed ISAC Systems
From Image- to Pixel-level: Label-efficient Hyperspectral Image Reconstruction
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios
AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution
Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
Emulating Self-attention with Convolution for Efficient Image Super-Resolution
GenDR: Lightning Generative Detail Restorator
Global graph features unveiled by unsupervised geometric deep learning
QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.