AAAI 2024 accepted papers on Point clouds
54 of the 2,864 papers accepted at AAAI 2024 (1.9%) are on Point clouds, compared with 1.5% at AAAI 2023. They fall into 4 topics.
See AAAI 2024 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 · 29 papers
- Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders (34 citations)
- Fast Inter-frame Motion Prediction for Compressed Dynamic Point Cloud Attribute Enhancement (26 citations)
- Interpretable3D: An Ad-Hoc Interpretable Classifier for 3D Point Clouds (23 citations)
- Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models (21 citations)
- SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation (21 citations)
- Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds (18 citations)
- SCP: Spherical-Coordinate-Based Learned Point Cloud Compression (18 citations)
- DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning (15 citations)
- Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack (14 citations)
- MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding (14 citations)
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification (13 citations)
- Invisible Backdoor Attack against 3D Point Cloud Classifier in Graph Spectral Domain (11 citations)
and 17 more in the interactive map.
Shape and surface completion · 13 papers
- PointAttN: You Only Need Attention for Point Cloud Completion (78 citations)
- Orthogonal Dictionary Guided Shape Completion Network for Point Cloud (31 citations)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (26 citations)
- CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers (25 citations)
- GridFormer: Point-Grid Transformer for Surface Reconstruction (19 citations)
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (17 citations)
- CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry (11 citations)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (10 citations)
- Robust 3D Tracking with Quality-Aware Shape Completion (10 citations)
- Locality Preserving Refinement for Shape Matching with Functional Maps (6 citations)
- Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection (5 citations)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (1 citation)
and 1 more in the interactive map.
Segmentation and detection · 10 papers
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (51 citations)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (29 citations)
- Frozen CLIP Transformer Is an Efficient Point Cloud Encoder (25 citations)
- VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding (24 citations)
- Improved MLP Point Cloud Processing with High-Dimensional Positional Encoding (10 citations)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (10 citations)
- Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation (9 citations)
- Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation (8 citations)
- iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds (7 citations)
- BEV-MAE: Bird’s Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios (1 citation)