PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.
hub
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
14 Pith papers cite this work, alongside 2,880 external citations. Polarity classification is still indexing.
14
Pith papers citing it
2,880
external citations · Pith
abstract
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
SBI framework with GNN-on-sets and masked autoregressive flow recovers input cosmologies from eRASS1 mocks at 11.5% precision on Ω_m and 4.4% on σ_8 using 3259 clusters.
SegviGen shows pretrained 3D generative models can be repurposed for part segmentation via voxel colorization, beating prior methods by 40% interactively and 15% on full segmentation using only 0.32% of labeled data.
Dual Grid Net is a two-stage FCN that regresses 3D hand mesh vertices and dense correspondences from single depth maps, achieving SOTA keypoint accuracy on NYU under supervision and competitive results via self-supervision without annotations.
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.
OPTNet adds a learnable ordering module with self-supervised loss to Point Transformers for improved efficiency and accuracy in post-disaster 3D semantic segmentation on the 3DAeroRelief dataset.
Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.
Linkify augments assembly graphs with corrected interface point clouds and trains GATv2 for masked part prediction, outperforming non-graph baselines on Fusion 360 data.
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.
Enwar 3.0 is an LLM-orchestrated framework that uses a sensor degradation classifier and context-aware agent coordination to achieve over 88% beam selection accuracy, 98% blockage F1-score, and 87% reasoning correctness in mmWave vehicular networks.
citing papers explorer
-
Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging
PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.
-
Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation
Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.
-
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
-
Simulation-Based Inference for Cluster Cosmology with Set-Based Neural Network Architectures
SBI framework with GNN-on-sets and masked autoregressive flow recovers input cosmologies from eRASS1 mocks at 11.5% precision on Ω_m and 4.4% on σ_8 using 3259 clusters.
-
SegviGen: Repurposing 3D Generative Model for Part Segmentation
SegviGen shows pretrained 3D generative models can be repurposed for part segmentation via voxel colorization, beating prior methods by 40% interactively and 15% on full segmentation using only 0.32% of labeled data.
-
Dual Grid Net: hand mesh vertex regression from single depth maps
Dual Grid Net is a two-stage FCN that regresses 3D hand mesh vertices and dense correspondences from single depth maps, achieving SOTA keypoint accuracy on NYU under supervision and competitive results via self-supervision without annotations.
-
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.
-
OPTNet: Ordering Point Transformer Network for Post-disaster 3D Semantic Segmentation
OPTNet adds a learnable ordering module with self-supervised loss to Point Transformers for improved efficiency and accuracy in post-disaster 3D semantic segmentation on the 3DAeroRelief dataset.
-
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.
-
Linkify: Learning from Interface-Augmented Assembly Graphs
Linkify augments assembly graphs with corrected interface point clouds and trains GATv2 for masked part prediction, outperforming non-graph baselines on Fusion 360 data.
-
Learning Representations from 3D Gaussian Splats
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.
-
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.
-
Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover Management
Enwar 3.0 is an LLM-orchestrated framework that uses a sensor degradation classifier and context-aware agent coordination to achieve over 88% beam selection accuracy, 98% blockage F1-score, and 87% reasoning correctness in mmWave vehicular networks.
- Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows