ScaLe-INR is a multi-branch INR architecture that applies directional scaling per the Fourier inverse theorem and a directional edge guidance loss to disentangle scales and improve reconstruction fidelity.
hub Mixed citations
Instant neural graph- ics primitives with a multiresolution hash encoding.ACM Transactions on Graphics (Proc
Mixed citation behavior. Most common role is background (60%).
31
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 3
baseline 1
method 1
citation-polarity summary
representative citing papers
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
HairGPT reframes 3D hairstyle synthesis as dual-decoupled autoregressive strand sequence modeling with geometric tokenization for semantic control and rare style generation.
RobotPan predicts metric-scaled compact 3D Gaussians from calibrated multi-view inputs via spherical coordinates and hierarchical voxel priors for real-time 360° robotic perception and reconstruction.
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
Introduces Visibility-Aware Densification with Temporally-Adaptive Thresholding and Temporal Offset Warping to improve dynamic region quality in 3D Gaussian Splatting on three benchmarks.
3D Gaussian transient rendering enables NLOS imaging from arbitrary relay geometries in both confocal and non-confocal setups, achieving SOTA on real measurements.
VisDom augments silhouette-based visual hull reconstruction with a minimum multi-view visibility constraint to supply a stronger geometric prior for sparse-view NeRF and GS optimization.
OctaOctree is a hybrid spatial-angular data structure for neural radiosity that enables real-time, high-quality rendering of glossy global illumination effects.
LEGS improves 3D Gaussian Splatting by replacing first-order edge guidance with second-order Laplacian structural guidance and nonlinear pixel-wise weighting, yielding up to 1.68 dB PSNR gain over baseline 3DGS on Tanks&Temples and Mip-NeRF360.
Controlled benchmarks show INR architectures differ in whether weight reuse is source-specific or generic, with no architecture dominating all PDE and analytic cases.
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
A physics-aware query-conditioned hierarchical graph attention network estimates point-wise transmitter-resolved radio maps from sparse measurements and outperforms baselines on DeepMIMO simulations in direct, residual, and gated regimes.
Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.
NeuVolEx extracts robust spatial features from INR training via a structural encoder and multi-task scheme to enable accurate ROI classification with limited supervision and unsupervised viewpoint clustering in volume exploration.
ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.
TouchAnything reconstructs accurate 3D object geometries from only a few tactile contacts by optimizing for consistency with a pretrained visual diffusion prior.
Patchwork is a new compact shape representation for 2D and 3D geometry that approximates arbitrary shapes with arbitrary precision using a small number of parameters, provable bounds, and gradient-based optimization with pruning regularization.
Multi-level DWT frequency modulation in 3DGS reduces Gaussian counts by recursive low-frequency decomposition and a single scaling parameter while preserving rendering quality.
RealLiFe optimizes multi-plane images with HSGD to deliver real-time light field reconstruction from sparse views, claiming 100x speedup over offline methods and 2 dB PSNR gain over online ones.
Hybrid system that uses ray-traced 3D Gaussians to supply radiometric guidance and material regularization to a neural renderer for editable, realistic output from captured scenes.
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
citing papers explorer
-
ScaLe-INR: Scale and Learn Implicit Neural Representations
ScaLe-INR is a multi-branch INR architecture that applies directional scaling per the Fourier inverse theorem and a directional edge guidance loss to disentangle scales and improve reconstruction fidelity.
-
Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
-
HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis
HairGPT reframes 3D hairstyle synthesis as dual-decoupled autoregressive strand sequence modeling with geometric tokenization for semantic control and rare style generation.
-
RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception
RobotPan predicts metric-scaled compact 3D Gaussians from calibrated multi-view inputs via spherical coordinates and hierarchical voxel priors for real-time 360° robotic perception and reconstruction.
-
LRM: Large Reconstruction Model for Single Image to 3D
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
-
Temporally Aware Densification for Dynamic 3D Gaussian Splatting
Introduces Visibility-Aware Densification with Temporally-Adaptive Thresholding and Temporal Offset Warping to improve dynamic region quality in 3D Gaussian Splatting on three benchmarks.
-
Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering
3D Gaussian transient rendering enables NLOS imaging from arbitrary relay geometries in both confocal and non-confocal setups, achieving SOTA on real measurements.
-
VisDom: Sparse Novel View Synthesis with Visible Domain Constraint
VisDom augments silhouette-based visual hull reconstruction with a minimum multi-view visibility constraint to supply a stronger geometric prior for sparse-view NeRF and GS optimization.
-
OctaOctree Neural Radiosity for Real-time Glossy Material Rendering
OctaOctree is a hybrid spatial-angular data structure for neural radiosity that enables real-time, high-quality rendering of glossy global illumination effects.
-
LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss
LEGS improves 3D Gaussian Splatting by replacing first-order edge guidance with second-order Laplacian structural guidance and nonlinear pixel-wise weighting, yielding up to 1.68 dB PSNR gain over baseline 3DGS on Tanks&Temples and Mip-NeRF360.
-
Architecture Shapes Transfer Specificity in Implicit Neural Representations
Controlled benchmarks show INR architectures differ in whether weight reuse is source-specific or generic, with no architecture dominating all PDE and analytic cases.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
-
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
-
You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
-
Physics-Aware Query-Conditioned Graph Attention Networks for Radio Map Estimation
A physics-aware query-conditioned hierarchical graph attention network estimates point-wise transmitter-resolved radio maps from sparse measurements and outperforms baselines on DeepMIMO simulations in direct, residual, and gated regimes.
-
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.
-
NeuVolEx: Implicit Neural Features for Volume Exploration
NeuVolEx extracts robust spatial features from INR training via a structural encoder and multi-task scheme to enable accurate ROI classification with limited supervision and unsupervised viewpoint clustering in volume exploration.
-
ANTIC: Adaptive Neural Temporal In-situ Compressor
ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.
-
TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches
TouchAnything reconstructs accurate 3D object geometries from only a few tactile contacts by optimizing for consistency with a pretrained visual diffusion prior.
-
Patchwork: A compact representation for 3D polygonal shapes
Patchwork is a new compact shape representation for 2D and 3D geometry that approximates arbitrary shapes with arbitrary precision using a small number of parameters, provable bounds, and gradient-based optimization with pruning regularization.
-
Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation
Multi-level DWT frequency modulation in 3DGS reduces Gaussian counts by recursive low-frequency decomposition and a single scaling parameter while preserving rendering quality.
-
RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent
RealLiFe optimizes multi-plane images with HSGD to deliver real-time light field reconstruction from sparse views, claiming 100x speedup over offline methods and 2 dB PSNR gain over online ones.
-
TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions
Hybrid system that uses ray-traced 3D Gaussians to supply radiometric guidance and material regularization to a neural renderer for editable, realistic output from captured scenes.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction
Hestia improves generalizable next-best-view planning for 3D reconstruction via hierarchical action search, diverse data, close-greedy strategy, and face-aware voxel design, yielding higher coverage and lower Chamfer distance than prior RL-based methods.
-
GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering
GaNI combines NeuS geometry reconstruction with a light-position-aware inverse neural radiosity stage that adds implicit near-field modeling, surface angle loss, and roughness smoothness priors to recover reflectance parameters from co-located light-camera captures.
-
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
OmniDreams is a real-time generative world model mid- and post-trained from the Cosmos diffusion model on 21k hours of driving data to autoregressively generate action-conditioned videos for closed-loop AV simulation.
-
Implicit neural representations as a coordinate-based framework for continuous environmental field reconstruction from sparse ecological observations
Implicit neural representations enable stable, resolution-independent reconstruction of continuous environmental fields from sparse and irregular ecological data.
-
Low-Cost Neural Radiance Fields
Comparative study of DS-NeRF, TensoRF, and HashNeRF with depth-supervision and architectural variants finds no conclusive outperformance under equal training time but identifies which design choices transfer to low-data, low-compute regimes.
-
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.
- TACO: Temporal Consensus Optimization for Continual Neural Mapping