Image Rescaling
18개 벤치마크 · 논문 26편 · 이 태스크의 논문 보기 →
Benchmarks
DIV2K val-q30-4x
DIV2K val-q50-4x
DIV2K val-q70-4x
DIV2K val-q90-4x
DIV2K val-q30-2x
DIV2K val-q50-2x
DIV2K val-q70-2x
DIV2K val-q90-2x
BSD100-2x
BSD100-4x
DIV2K val-2x
DIV2K val-4x
Set14-2x
Set14-4x
Set5-2x
Set5-4x
Urban100-2x
Urban100-4x
Most implemented
Invertible Image Rescaling
Geolocating Earth Imagery from ISS: Integrating Machine Learning with Astronaut Photography for Enhanced Geographic Mapping
Plug-and-Play Tri-Branch Invertible Block for Image Rescaling
Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images
Real-time 6K Image Rescaling with Rate-distortion Optimization
Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling
Papers
Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors
Most recent extreme rescaling methods struggle to preserve semantically consistent structures and produce realistic details, due to the severely ill-posed nature of low- to high-resolution mapping under scaling factors o…
Image RescalingEnhancing Low-resolution Image Representation Through Normalizing Flows
Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and tra…
Image RescalingEZREAL: Enhancing Zero-Shot Outdoor Robot Navigation toward Distant Targets under Varying Visibility
Zero-shot object navigation (ZSON) in large-scale outdoor environments faces many challenges; we specifically address a coupled one: long-range targets that reduce to tiny projections and intermittent visibility due to p…
Robot NavigationImage RescalingTackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
Reversible image conversion (RIC) suffers from ill-posedness issues due to its forward conversion process being considered an underdetermined system. Despite employing invertible neural networks (INN), existing RIC metho…
Image RescalingGeolocating Earth Imagery from ISS: Integrating Machine Learning with Astronaut Photography for Enhanced Geographic Mapping
This paper presents a novel approach to geolocating images captured from the International Space Station (ISS) using advanced machine learning algorithms. Despite having precise ISS coordinates, the specific Earth locati…
Deep LearningEarth Observationgeo-localizationImage Rescaling+4Plug-and-Play Tri-Branch Invertible Block for Image Rescaling
High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details. Recent advancements in image rescaling algorithms have employed inv…
Compressed Image Super-resolutionImage ReconstructionImage RescalingImage Super-Resolution