REVIEW 17 cited by
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
read the original abstract
Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.
Forward citations
Cited by 17 Pith papers
-
WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory
WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while e...
-
End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
An FPGA implementation of a neuromorphic auditory sensor plus graph neural network achieves 87.43% accuracy on Google Speech Commands v2 with sub-35 µs latency and 1.12 W power.
-
Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
Mix3R mixes feed-forward reconstruction and generative 3D priors via Mixture-of-Transformers and overlap-based attention bias to achieve better-aligned 3D shapes and more accurate poses than either approach alone.
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation
Grasp pretraining on 355k trajectories improves full-task success on six articulated tool-use tasks by 33.3 pp over DP3 in real-world experiments.
-
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.
-
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
Mapping point clouds to Fourier features improves high-precision imitation learning policies on RoboCasa, ManiSkill3, and real-robot tasks compared with Cartesian inputs.
-
Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence
A new MAT simplification algorithm uses explicit surface correspondence tracking and priority-controlled edge collapses to preserve structural features like fillet alignments on discrete meshes.
-
InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
InCoM achieves 23-28% higher success rates in mobile manipulation tasks by inferring motion intent for adaptive perception and decoupling base-arm action generation.
-
Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows
A human-in-the-loop pipeline generates usable segmented 2D atlases from diverse 3D geometries by using greedy view selection, SAM 2 interactive segmentation, and UV back-projection, with recurring manual corrections n...
-
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.
-
From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.
-
Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
Semantic Foam extends Radiant Foam with explicit cell-level semantic feature fields and spatial regularization to improve object segmentation consistency in scene representations.
-
Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
Semantic Foam unifies spatial Voronoi decomposition with cell-level semantic features to achieve superior object segmentation by enabling direct spatial regularization that avoids occlusion and view-inconsistency artifacts.
-
GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
GraphFusion3D reports improved 3D object detection accuracy on SUN RGB-D and ScanNetV2 by combining adaptive image-to-point fusion with multi-scale graph reasoning on proposals.
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.