MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
hub
Pointnet: Deep learning on point sets for 3d classification and segmentation
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
New lower bounds establish that Deep Sets need embedding dimension linear in the number of points (up to constants) for d>1, and give the first non-trivial bounds for higher-order Janossy pooling.
Characterizes monotone separating set functions with dimension bounds, proves non-existence on infinite domains, and introduces a Holder-stable neural model with a weak version of the property for universal monotone approximation.
GeoHand adapts priors from a general-scene geometry estimator via a GeoAdapter, gated fusion, and keypoint-queried refiner to reach SOTA monocular 3D hand reconstruction on FreiHAND, DexYCB, and HO3Dv3 under heavy occlusion.
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
RigidFormer learns mesh-free rigid dynamics from point clouds using object-centric anchors, Anchor-Vertex Pooling, Anchor-based RoPE, and differentiable Kabsch alignment to enforce rigidity.
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
Projecting 3D LiDAR to BEV images and applying YOLO-OBB with spatiotemporal fusion enables reliable real-time structural detection on resource-constrained robots.
Contour line features from 3D violin meshes outperform or match raw elevation maps when using SVM and decision trees to detect width reductions.
citing papers explorer
-
A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
-
Embedding Dimension Lower Bounds for Universality of Deep Sets and Janossy Pooling
New lower bounds establish that Deep Sets need embedding dimension linear in the number of points (up to constants) for d>1, and give the first non-trivial bounds for higher-order Janossy pooling.
-
Monotone and Separable Set Functions: Characterizations and Neural Models
Characterizes monotone separating set functions with dimension bounds, proves non-existence on infinite domains, and introduces a Holder-stable neural model with a weak version of the property for universal monotone approximation.
-
GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction
GeoHand adapts priors from a general-scene geometry estimator via a GeoAdapter, gated fusion, and keypoint-queried refiner to reach SOTA monocular 3D hand reconstruction on FreiHAND, DexYCB, and HO3Dv3 under heavy occlusion.
-
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
-
RigidFormer: Learning Rigid Dynamics using Transformers
RigidFormer learns mesh-free rigid dynamics from point clouds using object-centric anchors, Anchor-Vertex Pooling, Anchor-based RoPE, and differentiable Kabsch alignment to enforce rigidity.
-
Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
Real-Time Structural Detection for Indoor Navigation from 3D LiDAR Using Bird's-Eye-View Images
Projecting 3D LiDAR to BEV images and applying YOLO-OBB with spatiotemporal fusion enables reliable real-time structural detection on resource-constrained robots.
-
From Elevation Maps To Contour Lines: SVM and Decision Trees to Detect Violin Width Reduction
Contour line features from 3D violin meshes outperform or match raw elevation maps when using SVM and decision trees to detect width reductions.