AAAI 2025 accepted papers on Point clouds
75 of the 3,486 papers accepted at AAAI 2025 (2.2%) are on Point clouds, compared with 1.9% at AAAI 2024. They fall into 4 topics.
See AAAI 2025 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 · 37 papers
- Point Cloud Mamba: Point Cloud Learning via State Space Model (82 citations)
- PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning (26 citations)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (26 citations)
- AdaDPCC: Adaptive Rate Control and Rate-Distortion-Complexity Optimization for Dynamic Point Cloud Compression (22 citations)
- PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis (15 citations)
- Spiking Point Transformer for Point Cloud Classification (13 citations)
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (11 citations)
- Pamba: Enhancing Global Interaction in Point Clouds via State Space Model (9 citations)
- RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning (9 citations)
- Efficient 3D Recognition with Event-driven Spike Sparse Convolution (8 citations)
- Imperceptible 3D Point Cloud Attacks on Lattice-based Barycentric Coordinates (7 citations)
- Noise-Injected Spiking Graph Convolution for Energy-Efficient 3D Point Cloud Denoising (7 citations)
and 25 more in the interactive map.
Shape and surface completion · 17 papers
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (18 citations)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (11 citations)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (7 citations)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (5 citations)
- You Should Learn to Stop Denoising on Point Clouds in Advance (5 citations)
- DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer (4 citations)
- Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion (3 citations)
- Position-Aware Guided Point Cloud Completion with CLIP Model (3 citations)
- Scaling Diffusion Mamba with Bidirectional SSMs for Efficient 3D Shape Generation (3 citations)
- Sharpening Neural Implicit Functions with Frequency Consolidation Priors (3 citations)
- Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D Images (2 citations)
- DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence (1 citation)
and 5 more in the interactive map.
Segmentation and detection · 14 papers
- Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations (18 citations)
- Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation (15 citations)
- SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object Detection (6 citations)
- AS-Det: Active Sampling for Adaptive 3D Object Detection in Point Clouds (5 citations)
- A New Adversarial Perspective for LiDAR-based 3D Object Detection (3 citations)
- FEAST-Mamba: FEAture and SpaTial Aware Mamba Network with Bidirectional Orthogonal Fusion for Cross-Modal Point Cloud Segmentation (3 citations)
- 3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving (2 citations)
- Equirectangular Point Reconstruction for Domain Adaptive Multimodal 3D Object Detection in Adverse Weather Conditions (2 citations)
- Geometry-Aware 3D Salient Object Detection Network (2 citations)
- LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data (2 citations)
- MSV-PCT: Multi-Sparse-View Enhanced Transformer Framework for Salient Object Detection in Point Clouds (2 citations)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract)
and 2 more in the interactive map.
Registration and matching · 7 papers
- Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment (7 citations)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (6 citations)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (4 citations)
- Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration (4 citations)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (2 citations)
- Partial Point Cloud Registration with Multi-view 2D Image Learning (1 citation)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions