Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
hub
Dynamic graph cnn for learning on point clouds
14 Pith papers cite this work, alongside 6,738 external citations. Polarity classification is still indexing.
14
Pith papers citing it
6,738
external citations · OpenAlex
hub tools
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
representative citing papers
GoD uses anatomy graphs and difference alignment to improve medical image re-identification accuracy and auditability, with +7.1 pp Rank-1 gains on fundus and +3.1 pp on CXR.
UniField fuses discrete atomic graphs with continuous electron density fields via RBF guidance in an SE(3)-equivariant multimodal model, reporting new SOTA results on QM9-ED, QMugs-ED, and ED5-OE benchmarks with gains up to 37%.
A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
MAPR improves adversarial robustness in 3D point cloud networks by aligning latent predictions with intrinsic manifold geometry via curvature/diffusion features and a consistency loss.
Muon optimizer improves performance over Adam in equivariant networks on ModelNet40 and produces solutions with larger Hessian curvature, more regular loss surfaces, and higher stable/effective ranks.
Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.
TSegAgent performs zero-shot tooth instance segmentation and identification on 3D dental scans via multi-view foundation models plus explicit dental-arch geometric reasoning.
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
A 3D instance segmentation and attention-based re-identification pipeline for tracking fruits over time in colored point clouds, evaluated on strawberry and apple orchard data.
GaussFusion improves 3D Gaussian pre-training by adding image-text semantic alignment and a salience-guided multi-scale hole masking strategy, outperforming Gaussian-MAE on downstream 3D tasks.
Benchmark of federated learning plus knowledge distillation for point cloud classification reveals that label-free distillation objectives are required for student accuracy to reflect federated teacher quality rather than proxy labels.
A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.
citing papers explorer
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification
GoD uses anatomy graphs and difference alignment to improve medical image re-identification accuracy and auditability, with +7.1 pp Rank-1 gains on fundus and +3.1 pp on CXR.
-
UniField: RBF-Guided Electron Density Fusion for Enhanced Molecular Representations
UniField fuses discrete atomic graphs with continuous electron density fields via RBF guidance in an SE(3)-equivariant multimodal model, reporting new SOTA results on QM9-ED, QMugs-ED, and ED5-OE benchmarks with gains up to 37%.
-
Analogical Trajectory Transfer
A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.
-
Continuum Robot Modeling with Action Conditioned Flow Matching
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
-
Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
MAPR improves adversarial robustness in 3D point cloud networks by aligning latent predictions with intrinsic manifold geometry via curvature/diffusion features and a consistency loss.
-
How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
Muon optimizer improves performance over Adam in equivariant networks on ModelNet40 and produces solutions with larger Hessian curvature, more regular loss surfaces, and higher stable/effective ranks.
-
From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.
-
TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents
TSegAgent performs zero-shot tooth instance segmentation and identification on 3D dental scans via multi-view foundation models plus explicit dental-arch geometric reasoning.
-
Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
-
Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Colored Point Clouds
A 3D instance segmentation and attention-based re-identification pipeline for tracking fruits over time in colored point clouds, evaluated on strawberry and apple orchard data.
-
GaussFusion: Towards Multimodal 3D Gaussian Pretraining
GaussFusion improves 3D Gaussian pre-training by adding image-text semantic alignment and a salience-guided multi-scale hole masking strategy, outperforming Gaussian-MAE on downstream 3D tasks.
-
Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification
Benchmark of federated learning plus knowledge distillation for point cloud classification reveals that label-free distillation objectives are required for student accuracy to reflect federated teacher quality rather than proxy labels.
-
A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.