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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ec-jrc/humaint_annotator
공식 코드Attribute Annotation and Bias Evaluation in Visual Datasets for Autonomous Driving
https://github.com/edadepthmde/edadepth_icmla
공식 코드EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation
https://github.com/edongdongchen/DDN
공식 코드https://github.com/eduardzamfir/ntire23-rtsr
공식 코드Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey
https://github.com/eduardzamfir/seemoredetails
공식 코드See More Details: Efficient Image Super-Resolution by Experts Mining
https://github.com/eezkni/ddr
공식 코드DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
https://github.com/eezkni/fdl
공식 코드Misalignment-Robust Frequency Distribution Loss for Image Transformation
https://github.com/eezkni/ssiu
공식 코드Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution
https://github.com/egkang-luis/burstm
공식 코드BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow
https://github.com/eliahuhorwitz/conffusion
공식 코드https://github.com/emmajreid/MDF
공식 코드https://github.com/ensta-u2is/dido
공식 코드Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
https://github.com/enter-i-username/eigensr
공식 코드EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution
https://github.com/erichson/superbench
공식 코드SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning
https://github.com/esteban-rs/extracter
공식 코드https://github.com/esw0116/DynaVSR
공식 코드https://github.com/ethz-asl/tulip
공식 코드https://github.com/eugenelet/crfp
공식 코드Cross-Resolution Flow Propagation for Foveated Video Super-Resolution
https://github.com/eunjnnn/bfstvsr
공식 코드https://github.com/event-ahu/vfm-det
공식 코드VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models
https://github.com/evgeneybogatyrev/super-resolution-metric
공식 코드SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction
https://github.com/evgenyugolkov/8x_super-resolution
공식 코드https://github.com/ewrfcas/arci
공식 코드https://github.com/ewrfcas/leftrefill
공식 코드https://github.com/ewrfcas/pgic_inpainting
공식 코드https://github.com/explainableml/bayescap
공식 코드BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
https://github.com/eyalnaor/DeepTemporalSR
공식 코드Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning
https://github.com/eyeline-research/survey-video-diffusion
공식 코드Survey of Video Diffusion Models: Foundations, Implementations, and Applications
https://github.com/facebookresearch/dvsr
공식 코드Consistent Direct Time-of-Flight Video Depth Super-Resolution
https://github.com/falsr/FALSR
공식 코드Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
https://github.com/fanamber831/sgglc-net
공식 코드Semantic-Guided Global-Local Collaborative Networks for Lightweight Image Super-Resolution
https://github.com/fangchangma/sparse-to-dense
공식 코드Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
https://github.com/fangfang11-plog/adasr
공식 코드ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion
https://github.com/fanghua-yu/osrt
공식 코드OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer
https://github.com/fast-codi/CoDi
공식 코드CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.