TPAMI 2025 papers on Point clouds
35 of the 932 papers published in TPAMI 2025 (3.8%) are on Point clouds, compared with 5.9% at TPAMI 2024. They fall into 4 topics.
See TPAMI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Point cloud classification · 14 papers
- Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning (48 citations)
- Rethinking Efficient and Effective Point-Based Networks for Event Camera Classification and Regression (42 citations)
- Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark (24 citations)
- SPOT: Scalable 3D Pre-Training via Occupancy Prediction for Learning Transferable 3D Representations (16 citations)
- PointLLM-V2: Empowering Large Language Models to Better Understand Point Clouds (12 citations)
- Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning (8 citations)
- Towards Robust Point Cloud Recognition With Sample-Adaptive Auto-Augmentation (8 citations)
- Tri-Perspective View Decomposition for Geometry Aware Depth Completion and Super-Resolution (7 citations)
- Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations (6 citations)
- GPT4Point++: Advancing Unified Point-Language Understanding and Generation (4 citations)
- PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation (2 citations)
- Revisiting Siamese-Based 3D Single Object Tracking With a Versatile Transformer (2 citations)
and 2 more in the interactive map.
Segmentation and detection · 9 papers
- Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving (61 citations)
- MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection (43 citations)
- Generating Inverse Feature Space for Class Imbalance in Point Cloud Semantic Segmentation (41 citations)
- Quantity-Quality Enhanced Self-Training Network for Weakly Supervised Point Cloud Semantic Segmentation (23 citations)
- Self-Supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration (17 citations)
- Open-CRB: Toward Open World Active Learning for 3D Object Detection (11 citations)
- High-Quality Pseudo-Labeling for Point Cloud Segmentation With Scene-Level Annotation (1 citation)
- Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping (1 citation)
- Exploiting the Benefits of Temporal Information in the Realm of LiDAR Panoptic Segmentation
Registration and matching · 6 papers
- Non-Rigid Point Cloud Registration via Anisotropic Hybrid Field Harmonization (77 citations)
- SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration (8 citations)
- RKHS-BA: A Robust Correspondence-Free Multi-View Bundle Adjustment Framework for Semantic Point Clouds (3 citations)
- Iterative Differential Entropy Minimization (IDEM) Method for Fine Rigid Pairwise 3D Point Cloud Registration: A Focus on the Metric (1 citation)
- PAVM: Progressive and Adaptive Variance Minimization Algorithm for Robust Registration (1 citation)
- Single Voter Spreading for Efficient Correspondence Grouping and 3D Registration (1 citation)
Shape and surface completion · 6 papers
- DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fields (15 citations)
- Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images (14 citations)
- Monge-Ampere Regularization for Learning Arbitrary Shapes From Point Clouds (7 citations)
- I-Filtering: Implicit Filtering for Learning Neural Distance Functions From 3D Point Clouds (5 citations)
- FlexPara: Flexible Neural Surface Parameterization (4 citations)
- Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases
