A foveated imaging geometry CT (FIGCT) with mostly low-res detectors and a seeded diffusion model (DPFSR) enables global high-resolution CT reconstruction from limited high-res data.
Neurocomputing , volume =
4 Pith papers cite this work, alongside 663 external citations. Polarity classification is still indexing.
4
Pith papers citing it
663
external citations · OpenAlex
years
2026 4representative citing papers
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
FASR++ aggregates multi-frame facial features via a Feature Combiner into a diffusion model, yielding SOTA identity-preserving super-resolution and recognition gains on CelebA and Quis-Campi.
Flow matching achieves single-step pixel accuracy and 20-step perceptual quality for Sentinel-2 super-resolution, outperforming diffusion and Real-ESRGAN while enabling large-scale 2.5 m land-cover products.
citing papers explorer
-
Foveated-Imaging Geometry CT Architecture and Seeded Diffusion Model Enabling Global Super-Resolution Reconstruction
A foveated imaging geometry CT (FIGCT) with mostly low-res detectors and a seeded diffusion model (DPFSR) enables global high-resolution CT reconstruction from limited high-res data.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
-
Robust Face Super-Resolution and Recognition Through Multi-Feature Aggregation in Diffusion Models
FASR++ aggregates multi-frame facial features via a Feature Combiner into a diffusion model, yielding SOTA identity-preserving super-resolution and recognition gains on CelebA and Quis-Campi.
-
Flow matching for Sentinel-2 super-resolution: implementation, application, and implications
Flow matching achieves single-step pixel accuracy and 20-step perceptual quality for Sentinel-2 super-resolution, outperforming diffusion and Real-ESRGAN while enabling large-scale 2.5 m land-cover products.