NeurIPS 2023 accepted papers on Point clouds
46 of the 3,584 papers accepted at NeurIPS 2023 (1.3%) are on Point clouds, compared with 1.4% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 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 · 21 papers
- OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding (39 citations)
- PointGPT: Auto-regressively Generative Pre-training from Point Clouds (33 citations)
- Segment Any Point Cloud Sequences by Distilling Vision Foundation Models (29 citations)
- Real3D-AD: A Dataset of Point Cloud Anomaly Detection (19 citations)
- Spiking PointNet: Spiking Neural Networks for Point Clouds (16 citations)
- ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding (9 citations)
- CP-SLAM: Collaborative Neural Point-based SLAM System (8 citations)
- Explore In-Context Learning for 3D Point Cloud Understanding (8 citations)
- AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset (7 citations)
- GMSF: Global Matching Scene Flow (5 citations)
- A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions (4 citations)
- MiliPoint: A Point Cloud Dataset for mmWave Radar (4 citations)
and 9 more in the interactive map.
Shape and surface completion · 12 papers
- DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation (12 citations)
- InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion (6 citations)
- Point Cloud Completion with Pretrained Text-to-Image Diffusion Models (5 citations)
- NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function (4 citations)
- PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation (3 citations)
- $p$-Poisson surface reconstruction in curl-free flow from point clouds (2 citations)
- NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries (2 citations)
- Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model (2 citations)
- SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization (1 citation)
- VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation (1 citation)
- Aligning Gradient and Hessian for Neural Signed Distance Function
- Diverse Shape Completion via Style Modulated Generative Adversarial Networks
Segmentation and detection · 8 papers
- HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds (15 citations)
- Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion (13 citations)
- Uni3DETR: Unified 3D Detection Transformer (6 citations)
- Unleash the Potential of Image Branch for Cross-modal 3D Object Detection (5 citations)
- Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation (3 citations)
- Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination (3 citations)
- Unified 3D Segmenter As Prototypical Classifiers (2 citations)
- PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds (1 citation)
Registration and matching · 5 papers
- SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation (10 citations)
- Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching (9 citations)
- E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning (4 citations)
- Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration (4 citations)
- Non-Rigid Shape Registration via Deep Functional Maps Prior (3 citations)