GazePrior learns a 3D prior over eyes to synthesize realistic ground-truth data for training eye trackers on new devices without new real data collection.
hub
Nerf: Representing scenes as neural radiance fields for view synthesis.Communications of the ACM, 65(1):99–106
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis.
H2G distills 2D foundation-model affinities into a Lorentz hyperbolic feature field that represents hierarchical 3D groupings at multiple granularities.
PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.
Geo-EVS improves extrapolative novel view synthesis for driving scenes by conditioning on geometric maps from reprojections and training with artifact masks, leading to better quality and 3D detection on Waymo.
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
PEPS decomposes positional encodings into projected points with unique frequency-dependent motions to support more efficient learned grid-based encodings in INRs, outperforming prior methods on image, texture, and SDF tasks with often 25% fewer parameters.
A reference-free bootstrapped cross-validation method estimates performance of 4D deep-learning reconstruction from sparse X-ray data by comparing outputs from independent data subsets.
A quota-governor for Gaussian Splatting that tracks a quadratic target point count by adjusting existing hyperparameters, reaching the target by 15k iterations without hard cutoffs for fairer evaluations.
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.
citing papers explorer
-
GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction
GazePrior learns a 3D prior over eyes to synthesize realistic ground-truth data for training eye trackers on new devices without new real data collection.
-
Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations
Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis.
-
H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
H2G distills 2D foundation-model affinities into a Lorentz hyperbolic feature field that represents hierarchical 3D groupings at multiple granularities.
-
PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN
PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.
-
Geo-EVS: Geometry-Conditioned Extrapolative View Synthesis for Autonomous Driving
Geo-EVS improves extrapolative novel view synthesis for driving scenes by conditioning on geometric maps from reprojections and training with artifact masks, leading to better quality and 3D detection on Waymo.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
-
PEPS: Positional Encoding Projected Sampling -- Extended
PEPS decomposes positional encodings into projected points with unique frequency-dependent motions to support more efficient learned grid-based encodings in INRs, outperforming prior methods on image, texture, and SDF tasks with often 25% fewer parameters.
-
An evaluation framework for sparse 4D (3D + time) imaging reconstruction via bootstrapped cross-validation
A reference-free bootstrapped cross-validation method estimates performance of 4D deep-learning reconstruction from sparse X-ray data by comparing outputs from independent data subsets.
-
Smart target point control for Gaussian Splatting methods
A quota-governor for Gaussian Splatting that tracks a quadratic target point count by adjusting existing hyperparameters, reaching the target by 15k iterations without hard cutoffs for fairer evaluations.
-
Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.
-
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.