3D - Point Cloud

Paper list and Datasets about Point Cloud. Datasets can be found in Datasets.md.

Survey papers

• A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning [IJCAI 2024; Github]
• Sequential Point Clouds: A Survey [TPAMI 2024]
• End-to-end Autonomous Driving: Challenges and Frontiers [arXiv 2023; Github]
• 3D Object Detection for Autonomous Driving: A Comprehensive Survey [IJCV 2023; Github]
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey [TPAMI 2023; Github]
• 3D Object Detection from Images for Autonomous Driving: A Survey [TPAMI 2023; Github]
• Survey and Systematization of 3D Object Detection Models and Methods [TVC 2023]
• Multi-Modal 3D Object Detection in Autonomous Driving: a Survey [IJCV 2023]
• Cross-source Point Cloud Registration: Challenges, Progress and Prospects [Neurocomputing 2023]
• A Survey of Label-Efficient Deep Learning for 3D Point Clouds [arXiv 2023; Github]
• Self-Supervised Learning for Point Clouds Data: A Survey [ESWA 2023]
• Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey [arXiv 2023]
• Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review [IEEE T-IV 2023; Project]
• Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey [IEEE T-IV 2023]
• Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe [TPAMI 2023; Github]
• 3D Vision with Transformers: A Survey [arXiv 2022; Github]
• Vision-Centric BEV Perception: A Survey [arXiv 2022; Github]
• Transformers in 3D Point Clouds: A Survey [arXiv 2022]
• Surface Reconstruction from Point Clouds: A Survey and a Benchmark [arXiv 2022]
• A Survey of Robust LiDAR-based 3D Object Detection Methods for Autonomous Driving [arXiv 2022]
• A Survey of Non-Rigid 3D Registration [Eurographics 2022]
• Comprehensive Review of Deep Learning-Based 3D Point Clouds Completion Processing and Analysis [TITS 2022]
• Multi-modal Sensor Fusion for Auto Driving Perception: A Survey [arXiv 2022]
• 3D Object Detection for Autonomous Driving: A Survey [Pattern Recognition 2022; Github]
• 3D Semantic Scene Completion: a Survey [IJCV 2022]
• Deep Learning based 3D Segmentation: A Survey [arXiv 2021]
• A comprehensive survey on point cloud registration [arXiv 2021]
• Deep Learning for 3D Point Clouds: A Survey [TPAMI 2020; Github]
• A Comprehensive Performance Evaluation of 3D Local Feature Descriptors [IJCV 2016]

2024

• ECCV
  • Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene [det]
  • Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection [det]
  • OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection [det]
  • SEED: A Simple and Effective 3D DETR in Point Clouds [det]
  • General Geometry-aware Weakly Supervised 3D Object Detection [det; PyTorch]
  • SegPoint: Segment Any Point Cloud via Large Language Model [seg]
  • Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models [seg]
  • ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation [seg]
  • RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation [seg]
  • 3×2: 3D Object Part Segmentation by 2D Semantic Correspondences [seg]
  • Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation [seg]
  • SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds [seg]
  • HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation [seg; PyTorch]
  • Part2Object: Hierarchical Unsupervised 3D Instance Segmentation [seg; PyTorch]
  • 4D Contrastive Superflows are Dense 3D Representation Learners [pre-training]
  • Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data [pre-training]
  • Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion [completion; PyTorch]
  • T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy [completion; Github]
  • GaussReg: Fast 3D Registration with Gaussian Splatting [registration]
  • ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency [registration; PyTorch]
  • Transferable 3D Adversarial Shape Completion using Diffusion Models [adversarial attack]
  • R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [anomaly detection]
• CVPR
  • Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis [pre-training; PyTorch]
  • HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes [det]
  • Commonsense Prototype for Outdoor Unsupervised 3D Object Detection [det; PyTorch]
  • Point Transformer V3: Simpler, Faster, Stronger [seg, det; Github]
  • OneFormer3D: One Transformer for Unified Point Cloud Segmentation [seg; Github]
  • Rethinking Few-shot 3D Point Cloud Semantic Segmentation [seg; PyTorch]
  • CurveCloudNet: Processing Point Clouds with 1D Structure [seg]
  • No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation [seg; PyTorch]
  • TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation [seg]
  • GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds [seg; PyTorch]
  • Multi-Space Alignments Towards Universal LiDAR Segmentation [seg; Github]
  • KPConvX: Modernizing Kernel Point Convolution with Kernel Attention [cls, seg]
  • X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition [cls, seg; PyTorch]
  • Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding [cls, seg; PyTorch]
  • Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching [matching]
  • Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension [registration; Github]
  • Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes [registration; Github]
  • FastMAC: Stochastic Spectral Sampling of Correspondence Graph [registration; Github]
  • Scalable 3D Registration via Truncated Entry-wise Absolute Residuals [registration; Github]
  • Category-Level Multi-Part Multi-Joint 3D Shape Assembly [shape assembly]
  • Symphonize 3D Semantic Scene Completion with Contextual Instance Queries [semantic scene completion; PyTorch]
  • PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation [semantic occupancy prediction; Github]
  • Visual Point Cloud Forecasting enables Scalable Autonomous Driving [autonomous driving; Github]
  • Object Dynamics Modeling with Hierarchical Point Cloud-based Representations [autonomous driving; PyTorch]
  • Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes [reconstruction]
  • Unleashing Network Potentials for Semantic Scene Completion [completion]
  • FSC: Few-point Shape Completion [completion]
  • Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange [self-supervised; Github]
  • GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding [self-supervised]
  • SemCity: Semantic Scene Generation with Triplane Diffusion [generation]
  • Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds [adversarial attack; Github]
  • StraightPCF: Straight Point Cloud Filtering [filtering; Github]
  • [Unsupervised Occupancy