AAAI 2023 accepted papers on Point clouds
31 of the 2,023 papers accepted at AAAI 2023 (1.5%) are on Point clouds, compared with 1.8% at AAAI 2022. They fall into 4 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Point cloud classification · 16 papers
- GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds (50 citations)
- OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression with Local Enhancement (40 citations)
- TransLO: A Window-Based Masked Point Transformer Framework for Large-Scale LiDAR Odometry (37 citations)
- Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization (33 citations)
- GAM: Gradient Attention Module of Optimization for Point Clouds Analysis (21 citations)
- Boosting Point Clouds Rendering via Radiance Mapping (17 citations)
- Deep Manifold Attack on Point Clouds via Parameter Plane Stretching (17 citations)
- Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning (16 citations)
- Text to Point Cloud Localization with Relation-Enhanced Transformer (13 citations)
- PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration (12 citations)
- PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models against Adversarial Examples (12 citations)
- CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame (9 citations)
and 4 more in the interactive map.
Segmentation and detection · 11 papers
- SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud (49 citations)
- MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection (30 citations)
- PUPS: Point Cloud Unified Panoptic Segmentation (24 citations)
- Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network (22 citations)
- SEFormer: Structure Embedding Transformer for 3D Object Detection (20 citations)
- CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion (18 citations)
- Cross-Modal Contrastive Learning for Domain Adaptation in 3D Semantic Segmentation (18 citations)
- LWSIS: LiDAR-Guided Weakly Supervised Instance Segmentation for Autonomous Driving (16 citations)
- Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency (8 citations)
- Geometry-Aware Network for Domain Adaptive Semantic Segmentation (6 citations)
- Context-Aware Transformer for 3D Point Cloud Automatic Annotation (5 citations)
Shape and surface completion · 3 papers
Registration and matching · 1 paper
- Rethinking Rotation Invariance with Point Cloud Registration (11 citations)