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.
hub
The unreasonable effectiveness of deep features as a perceptual metric
24 Pith papers cite this work. Polarity classification is still indexing.
24
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.
PSG-UIENet fuses Retinex physics with CLIP-derived text semantics and a new multimodal dataset to enhance underwater images, claiming better results than fifteen prior methods.
Two MoE integration strategies (joint canonical MoDE vs. independent-then-route MoE-GS) improve dynamic Gaussian Splatting by composing complementary deformation priors.
Hierarchical anti-aesthetic adversarial noise, guided by global and face-local preference reward models, degrades customized diffusion outputs and reduces facial identity leakage more than prior cloaking methods.
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
The paper proposes the Degradation Frequency Curve (DFC) as an explicit spectral representation for quantifying degradations and develops a DFC-guided multi-scale restorer that achieves state-of-the-art performance on composite and real-world benchmarks.
D2-CDIG conditions diffusion models on DEM and cloud-fog priors to generate controlled remote sensing images with decoupled terrain and atmospheric control.
InkDiffuser generates high-fidelity one-shot Chinese calligraphy using high-frequency enhancement and a differentiable ink structure loss for realistic stroke and ink rendering.
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.
DailyArt recovers full joint parameters of articulated objects from a single static image by synthesizing an opened state and comparing discrepancies, supporting downstream part-level novel state synthesis.
NC-Diffusion matches quantization noise to the diffusion forward process, adds an adaptive frequency filter and zero-shot enhancement, and reports superior fidelity on benchmarks.
Lumos3D enables pose-free single-forward restoration of low-light 3D scenes via cross-illumination distillation from a teacher network and a custom Lumos loss on 3D Gaussians.
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
LiDAR-reflectance-guided Salient Gaussians improve self-driving scene reconstruction under high ego-motion and complex lighting, beating OmniRe by 1.18 dB PSNR on Waymo Complex Lighting.
A real-time underwater SLAM system uses reliability-aware multi-sensor fusion and quadtree-guided 3D Gaussian mapping to maintain localization and photorealistic reconstruction during visual degradation.
FaceCloak learns a lightweight identity-specific cloaking mask from a single image via synthetic face generation and iterative embedding perturbation to evade multiple recognition models.
Trajectory-guided diffusion synthesis reconstructs missing frames in top-down drone videos of maritime maneuvers, outperforming optical flow extrapolation and RIFE interpolation on perceptual quality, motion realism, and trajectory adherence metrics.
MesonGS++ achieves over 34x compression of 3D Gaussian Splatting models post-training while preserving or exceeding original rendering quality through size-aware hyperparameter optimization.
SALD decouples remote sensing images into compressed payload plus structural prior at the edge and uses structure-gated diffusion on the cloud to improve super-resolution and downstream detection under extreme bandwidth limits.
Scene-adaptive lattice vector quantization improves rate-distortion performance of 3DGS compression over uniform scalar quantization while adding little overhead and supporting multiple bit rates from one trained model.
3DCarGen synthesizes 3D-consistent multi-view images from one input photo, builds a coarse 3D Gaussian representation, then generates arbitrary views and recovers detailed meshes with color-normal optimization for real-world car images.
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.
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.
-
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.
-
Retinex Meets Language: A Physics-Semantics-Guided Underwater Image Enhancement Network
PSG-UIENet fuses Retinex physics with CLIP-derived text semantics and a new multimodal dataset to enhance underwater images, claiming better results than fifteen prior methods.
-
On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting
Two MoE integration strategies (joint canonical MoDE vs. independent-then-route MoE-GS) improve dynamic Gaussian Splatting by composing complementary deformation priors.
-
Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models
Hierarchical anti-aesthetic adversarial noise, guided by global and face-local preference reward models, degrades customized diffusion outputs and reduces facial identity leakage more than prior cloaking methods.
-
AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
-
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
The paper proposes the Degradation Frequency Curve (DFC) as an explicit spectral representation for quantifying degradations and develops a DFC-guided multi-scale restorer that achieves state-of-the-art performance on composite and real-world benchmarks.
-
D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog
D2-CDIG conditions diffusion models on DEM and cloud-fog priors to generate controlled remote sensing images with decoupled terrain and atmospheric control.
-
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.
-
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.
-
DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics
DailyArt recovers full joint parameters of articulated objects from a single static image by synthesizing an opened state and comparing discrepancies, supporting downstream part-level novel state synthesis.
-
A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
NC-Diffusion matches quantization noise to the diffusion forward process, adds an adaptive frequency filter and zero-shot enhancement, and reports superior fidelity on benchmarks.
-
Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration
Lumos3D enables pose-free single-forward restoration of low-light 3D scenes via cross-illumination distillation from a teacher network and a custom Lumos loss on 3D Gaussians.
-
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
-
LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction
LiDAR-reflectance-guided Salient Gaussians improve self-driving scene reconstruction under high ego-motion and complex lighting, beating OmniRe by 1.18 dB PSNR on Waymo Complex Lighting.
-
APVI-SLAM: Real-Time Acoustic-Pressure-Visual-Inertial Localization and Photorealistic Mapping System in Complex Underwater Environment
A real-time underwater SLAM system uses reliability-aware multi-sensor fusion and quadtree-guided 3D Gaussian mapping to maintain localization and photorealistic reconstruction during visual degradation.
-
Personalized Face Privacy Protection From a Single Image
FaceCloak learns a lightweight identity-specific cloaking mask from a single image via synthetic face generation and iterative embedding perturbation to evade multiple recognition models.
-
Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance
Trajectory-guided diffusion synthesis reconstructs missing frames in top-down drone videos of maritime maneuvers, outperforming optical flow extrapolation and RIFE interpolation on perceptual quality, motion realism, and trajectory adherence metrics.
-
MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
MesonGS++ achieves over 34x compression of 3D Gaussian Splatting models post-training while preserving or exceeding original rendering quality through size-aware hyperparameter optimization.
-
Edge-Cloud Collaborative Reconstruction via Structure-Aware Latent Diffusion for Downstream Remote Sensing Perception
SALD decouples remote sensing images into compressed payload plus structural prior at the edge and uses structure-gated diffusion on the cloud to improve super-resolution and downstream detection under extreme bandwidth limits.
-
Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
Scene-adaptive lattice vector quantization improves rate-distortion performance of 3DGS compression over uniform scalar quantization while adding little overhead and supporting multiple bit rates from one trained model.
-
3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis
3DCarGen synthesizes 3D-consistent multi-view images from one input photo, builds a coarse 3D Gaussian representation, then generates arbitrary views and recovers detailed meshes with color-normal optimization for real-world car images.
-
NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.
- IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions