MetaEarth-MM unifies multi-modal remote sensing image generation and any-to-any translation across five modalities via scene-centered joint modeling on the new EarthMM dataset.
Image-to-image translation with conditional adversarial networks,
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Neural implicit functions enable resolution-agnostic, deterministic virtual staining from H&E to IHC images with SOTA results and better low-data performance than patch-based GAN or diffusion methods.
A privacy-preserving thermal-only crowd counting framework extracts enhanced features from thermal images via single-step LCM denoising in a depth-to-RGB diffusion model and matches RGB-T fusion performance without RGB input at inference.
InkDiffuser generates high-fidelity one-shot Chinese calligraphy using high-frequency enhancement and a differentiable ink structure loss for realistic stroke and ink rendering.
DECIFR shows that public standard cell library layouts enable a no-auxiliary-data membership inference attack on federated gradient updates by correlating reconstruction quality with training membership in integrated circuit datasets.
StructDiff adds adaptive receptive fields and 3D positional encoding to a single-scale diffusion model to preserve structure and enable spatial control in single-image generation.
An I²SB diffusion model for CT FOV extension delivers RMSE of 49.8 HU on simulated data and 152.0 HU on real data with 0.19 s per-slice inference, over 700 times faster than cDDPM.
citing papers explorer
-
MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling
MetaEarth-MM unifies multi-modal remote sensing image generation and any-to-any translation across five modalities via scene-centered joint modeling on the new EarthMM dataset.
-
IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions
Neural implicit functions enable resolution-agnostic, deterministic virtual staining from H&E to IHC images with SOTA results and better low-data performance than patch-based GAN or diffusion methods.
-
Thermal-Only Crowd Counting with Deployment-Time Privacy Protection
A privacy-preserving thermal-only crowd counting framework extracts enhanced features from thermal images via single-step LCM denoising in a depth-to-RGB diffusion model and matches RGB-T fusion performance without RGB input at inference.
-
InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization
InkDiffuser generates high-fidelity one-shot Chinese calligraphy using high-frequency enhancement and a differentiable ink structure loss for realistic stroke and ink rendering.
-
DECIFR: Domain-Aware Exfiltration of Circuit Information from Federated Gradient Reconstruction
DECIFR shows that public standard cell library layouts enable a no-auxiliary-data membership inference attack on federated gradient updates by correlating reconstruction quality with training membership in integrated circuit datasets.
-
StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation
StructDiff adds adaptive receptive fields and 3D positional encoding to a single-scale diffusion model to preserve structure and enable spatial control in single-image generation.
-
Efficient Image-to-Image Schr\"odinger Bridge for CT Field of View Extension
An I²SB diffusion model for CT FOV extension delivers RMSE of 49.8 HU on simulated data and 152.0 HU on real data with 0.19 s per-slice inference, over 700 times faster than cDDPM.