Papers with Code 아카이브

Reference-based Super-Resolution

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Reference-based Super-Resolution aims to recover high-resolution images by utilizing external reference images containing similar content to generate rich textures.

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

HiTSR: A Hierarchical Transformer for Reference-based Super-Resolution

Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network

MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References

Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations

Detail-Enhancing Framework for Reference-Based Image Super-Resolution

Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model

HSTR-Net: Reference Based Video Super-resolution with Dual Cameras

A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution

Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

Multi-Reference Image Super-Resolution: A Posterior Fusion Approach

Reference-based Image and Video Super-Resolution via C2-Matching

Reference-based Image Super-Resolution with Deformable Attention Transformer

HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area Surveillance

Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

Dual-Camera Super-Resolution with Aligned Attention Modules

Robust Reference-based Super-Resolution via C2-Matching

A Frequency Domain Constraint for Synthetic and Real X-ray Image Super Resolution

Image Super-Resolution by Neural Texture Transfer

CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping

Reference-Conditioned Super-Resolution by Neural Texture Transfer

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.